© 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. 71275
    Prev
    Next
    INDEX
    Explanations

    standard deviation SD

    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
     ……
    -2.25
     tainted
    -2.16
     This
    -2.05
     ….
    -2.03
    沒有
    -2.02
     ─
    -1.98
     此
    -1.95
     नहीं
    -1.93
     ......
    -1.93
     ,"
    -1.91
    POSITIVE LOGITS
     maman
    2.22
    ＞＞
    2.17
     jajaja
    2.17
    鱨
    2.17
    醅
    2.13
     crudo
    2.09
     jaja
    2.05
    𓍊
    2.05
     saha
    2.03
     maky
    2.00
    Activations Density 0.003%

    No Known Activations