© 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. 73796
    Prev
    Next
    INDEX
    Explanations

    coverage of

    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
     There
    -2.91
    {
    -2.91
    ר
    -2.86
    }
    -2.84
    埽
    -2.73
     '
    -2.48
    🎉
    -2.42
    '
    -2.34
    end
    -2.33
    锺
    -2.33
    POSITIVE LOGITS
    趼
    3.20
     of
    3.08
    踅
    2.97
    
    2.95
    弍
    2.78
    先は
    2.73
    螓
    2.70
    欵
    2.67
    部分は
    2.61
    Ꭽ
    2.61
    Activations Density 0.003%

    No Known Activations