© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107857
    Prev
    Next
    INDEX
    Explanations

    code structure and metadata

    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
    simi
    -0.72
    魅
    -0.70
    nser
    -0.69
     κρα
    -0.69
    ÓW
    -0.68
    отно
    -0.68
    IDENTS
    -0.67
    acorn
    -0.67
     Fusion
    -0.66
    ismas
    -0.66
    POSITIVE LOGITS
     Tul
    0.66
     commute
    0.64
    ẻ
    0.63
    刻
    0.62
     справед
    0.62
    考核
    0.62
     altro
    0.61
    Style
    0.61
    マリ
    0.60
    newtheorem
    0.59
    Activations Density 0.051%

    No Known Activations