© 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. 63371
    Prev
    Next
    INDEX
    Explanations

    software distributed under

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    先生
    -0.72
    issi
    -0.71
    좌
    -0.70
    addRow
    -0.69
    ort
    -0.68
     Aero
    -0.67
    นาย
    -0.67
    INSERT
    -0.67
    ТЕ
    -0.66
    鞭
    -0.66
    POSITIVE LOGITS
    いたら
    0.71
    quire
    0.66
    梶
    0.66
    Fet
    0.64
    ears
    0.64
    BRARY
    0.63
    blooded
    0.63
     olympique
    0.63
    लब्
    0.63
     YY
    0.62
    Activations Density 0.147%

    No Known Activations