© 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. 113418
    Prev
    Next
    INDEX
    Explanations

    vinyl records and players

    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
     gider
    -1.45
    自己的
    -1.41
     indication
    -1.37
    was
    -1.31
    ஊ
    -1.30
    Ꭴ
    -1.30
    else
    -1.27
     apache
    -1.27
     cinese
    -1.27
    夕食
    -1.26
    POSITIVE LOGITS
     Vordergrund
    1.56
    
    1.52
    ж
    1.39
    
    1.38
     luchar
    1.37
     trabajan
    1.34
    鵡
    1.34
    NECTIONS
    1.34
     světa
    1.34
     we
    1.34
    Activations Density 0.019%

    No Known Activations