© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108372
    Prev
    Next
    INDEX
    Explanations

    acids

    np_acts-logits-general · gemini-2.5-flash-lite

    document headers and metadata sections in formatted content.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron responds to standalone numeric tokens (pure numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    line breaks or paragraph boundaries in structured text, particularly in formatted documents like code, product descriptions, and legal text.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    document-structure markers such as titles/headings, metadata fields, and license/legal boilerplate lines, often at section breaks.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olge
    -1.13
     Nissan
    -1.06
    chage
    -1.05
    
    -0.97
    already
    -0.96
    ᾽
    -0.93
     polling
    -0.92
    isat
    -0.91
     VALVE
    -0.91
    providedIn
    -0.90
    POSITIVE LOGITS
     обеспечить
    0.88
     uovo
    0.86
    哇
    0.84
    Integral
    0.83
    Transcripción
    0.81
     рассказать
    0.81
     seemingly
    0.81
    既然
    0.81
     Yep
    0.80
    Seam
    0.80
    Activations Density 0.000%

    No Known Activations