© 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. 34-GEMMASCOPE-RES-131K
    7. 38090
    Prev
    Next
    INDEX
    Explanations

    in source

    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_34/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
    rendo
    -0.70
    anele
    -0.65
    樣的
    -0.64
    ingu
    -0.63
    اة
    -0.63
     arch
    -0.62
    讫
    -0.61
    acty
    -0.60
    声道
    -0.60
    銳
    -0.60
    POSITIVE LOGITS
    Disse
    0.71
    PHeader
    0.69
    鞋
    0.69
    SILVER
    0.68
    ರೆ
    0.67
     alters
    0.66
     Wasserstoff
    0.66
     تجمع
    0.66
    腾讯
    0.65
    tablissement
    0.64
    Activations Density 0.113%

    No Known Activations