© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 104279
    Prev
    Next
    INDEX
    Explanations

    specifics in styles

    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
     phénom
    -1.11
    ژگی
    -1.00
    ergies
    -1.00
     bicara
    -0.95
    Ответы
    -0.94
    🔅
    -0.92
    Ữ
    -0.92
    aguer
    -0.92
     untuk
    -0.92
    entown
    -0.92
    POSITIVE LOGITS
     style
    2.08
     inspired
    1.66
     type
    1.55
     Inspired
    1.39
     styled
    1.38
    inspired
    1.38
    like
    1.37
     comparable
    1.34
    style
    1.33
     benzer
    1.27
    Activations Density 0.148%

    No Known Activations