© 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. 22036
    Prev
    Next
    INDEX
    Explanations

    make room for

    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
     geholfen
    -1.75
    .
    -1.62
    en
    -1.55
     многих
    -1.53
     avesse
    -1.48
    A
    -1.47
    of
    -1.45
    would
    -1.45
     dennoch
    -1.45
     voran
    -1.43
    POSITIVE LOGITS
     in
    1.95
    <>
    1.90
     also
    1.89
     by
    1.75
     for
    1.72
    AutoModerator
    1.68
    ům
    1.66
    ăți
    1.66
    leyin
    1.65
    }_{\
    1.55
    Activations Density 0.017%

    No Known Activations