© 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. 10-GEMMASCOPE-RES-131K
    7. 85256
    Prev
    Next
    INDEX
    Explanations

    people, games, data, nominees

    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
     foran
    -1.52
     autre
    -1.47
    欺负
    -1.41
     presque
    -1.38
     ////
    -1.36
     uniquement
    -1.35
     automatiquement
    -1.35
     Руси
    -1.34
     certains
    -1.34
     secondes
    -1.34
    POSITIVE LOGITS
     including
    2.17
     with
    2.11
     from
    2.09
     in
    2.03
     the
    2.02
     on
    1.98
     they
    1.96
     by
    1.90
     their
    1.90
     that
    1.77
    Activations Density 0.192%

    No Known Activations