© 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. 73381
    Prev
    Next
    INDEX
    Explanations

    ICS, Makefile, Boh

    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
    ௅
    -3.39
    ဴ
    -3.09
    縯
    -3.00
    目前的
    -2.98
    鳏
    -2.89
     surprisingly
    -2.89
    渽
    -2.78
    鏵
    -2.78
     был
    -2.75
    秕
    -2.75
    POSITIVE LOGITS
    .
    3.56
    {
    3.28
    2.97
    ta
    2.75
    ↵↵
    2.73
     
    2.70
    ,
    2.70
     I
    2.61
    '
    2.59
    䜣
    2.58
    Activations Density 0.023%

    No Known Activations