© 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. 10-GEMMASCOPE-RES-131K
    7. 40065
    Prev
    Next
    INDEX
    Explanations

    award-winning

    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_10/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
    ”
    -2.36
     -
    -2.09
    et
    -2.08
    也不用
    -2.08
    ins
    -1.99
    >
    -1.93
    轳
    -1.88
    ó
    -1.88
    ・・・」
    -1.87
    {
    -1.82
    POSITIVE LOGITS
    ه
    2.22
    焄
    2.20
    ！！”
    2.09
    ו
    2.09
    鸯
    2.06
    锇
    1.99
    ！！！”
    1.99
    ଼
    1.98
    ？！”
    1.96
    cyklopedia
    1.88
    Activations Density 0.008%

    No Known Activations