© 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. 70377
    Prev
    Next
    INDEX
    Explanations

    std::string usage

    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
     in
    -1.80
    '
    -1.75
    ！』
    -1.68
     with
    -1.67
    uría
    -1.66
    That
    -1.66
    ginous
    -1.62
    がありました
    -1.61
    asanjo
    -1.60
    quirer
    -1.59
    POSITIVE LOGITS
    枼
    1.84
    他
    1.71
    趼
    1.62
    炻
    1.61
    她
    1.59
    YNAM
    1.57
    我
    1.55
    我们
    1.49
     剧照
    1.48
     Bulan
    1.45
    Activations Density 0.004%

    No Known Activations