© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30976
    Prev
    Next
    INDEX
    Explanations

    medical patients

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

    line breaks in structured text documents.

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

    The neuron is activated by and thereby detects numeric tokens (numbers).

    oai_token-act-pair · o4-miniTriggered 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
     should
    -0.88
     abusos
    -0.82
     mostly
    -0.81
     złot
    -0.81
    physik
    -0.77
     noiva
    -0.77
     meticulous
    -0.76
     begy
    -0.75
    ๔
    -0.73
    meja
    -0.72
    POSITIVE LOGITS
     conflic
    0.94
    ziger
    0.93
    uli
    0.89
     новую
    0.89
    —.
    0.86
    {{/
    0.85
     يا
    0.84
     libert
    0.83
    ades
    0.83
     хорошее
    0.81
    Activations Density 0.001%

    No Known Activations