© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 15799
    Prev
    Next
    INDEX
    Explanations

    quantities, percentages, stages, distribution

    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_22/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
     правительства
    -2.08
     パソコン
    -1.74
     chré
    -1.66
     cuivre
    -1.59
     السياس
    -1.55
     设置
    -1.52
     книг
    -1.46
    iStock
    -1.42
     获取
    -1.41
     recensement
    -1.41
    POSITIVE LOGITS
     مباراة
    1.82
    ῾
    1.73
     regione
    1.53
     फिल्म
    1.52
    購入した
    1.50
     سينما
    1.45
     Francus
    1.41
    🛻
    1.36
     الشاشة
    1.32
     ملابس
    1.31
    Activations Density 0.148%

    No Known Activations