© 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. 58427
    Prev
    Next
    INDEX
    Explanations

    proper names or code relations

    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
    ᠁
    -2.83
    喈
    -2.70
    .
    -2.69
    not
    -2.63
     современных
    -2.48
    you
    -2.47
    ஂ
    -2.44
     唯美
    -2.39
     comprised
    -2.38
    ization
    -2.31
    POSITIVE LOGITS
    狁
    2.53
    ()){
    2.45
    AutoresizingMask
    2.38
    sterreich
    2.34
     verhind
    2.31
     кухо
    2.30
    韭菜
    2.27
    cipline
    2.20
    pecabe
    2.16
    ᚻ
    2.14
    Activations Density 0.013%

    No Known Activations