© 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. 48604
    Prev
    Next
    INDEX
    Explanations

    Kidney cysts, clinical manifestations

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

    programming syntax elements such as variables, operators, and brackets in code.

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

    The neuron activates on numeric tokens (integer literals or digit sequences).

    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
    已经是
    -0.98
     stratég
    -0.92
     rahasia
    -0.90
     ratusan
    -0.89
    spyOn
    -0.89
     leto
    -0.88
    ciptakan
    -0.88
     geheim
    -0.87
     ulasan
    -0.84
    middag
    -0.84
    POSITIVE LOGITS
     emplace
    1.02
     Liabilities
    0.91
    MAXN
    0.91
     Runoff
    0.87
    ตุ
    0.87
    ;">
    0.87
     Ashraf
    0.84
     Liability
    0.84
    now
    0.83
    スキル
    0.83
    Activations Density 0.007%

    No Known Activations