© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 38331
    Prev
    Next
    INDEX
    Explanations

    Reading controller 0

    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_34/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
     cuchillo
    -0.82
     turrets
    -0.73
    Selfer
    -0.72
    يح
    -0.71
    ferences
    -0.71
    няка
    -0.70
    たくない
    -0.70
    潞
    -0.69
     Heist
    -0.69
     Autonomous
    -0.68
    POSITIVE LOGITS
    เต
    0.73
    껍
    0.67
    関係
    0.67
    шер
    0.60
    批評
    0.60
    ற
    0.60
     abol
    0.59
     besuchen
    0.59
     sown
    0.59
    quiry
    0.58
    Activations Density 0.059%

    No Known Activations