© 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. 14825
    Prev
    Next
    INDEX
    Explanations

    search in code or data

    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
    泐
    -2.23
    厹
    -2.03
     comienzos
    -2.00
    ?”
    -2.00
    翃
    -1.95
     表情
    -1.92
     また
    -1.88
     значительно
    -1.85
     Können
    -1.83
    一部分
    -1.80
    POSITIVE LOGITS
    ar
    2.23
    3
    2.19
    in
    2.06
    an
    2.03
    ㆆ
    2.02
    a
    1.99
    able
    1.97
    '
    1.96
    it
    1.95
    樣子
    1.95
    Activations Density 0.011%

    No Known Activations