© 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. 94165
    Prev
    Next
    INDEX
    Explanations

    padding and geometry

    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
     passes
    -0.89
     himself
    -0.88
     taken
    -0.74
     ungkap
    -0.72
     hidratante
    -0.71
    NameExpr
    -0.70
     /\.(
    -0.69
     требуется
    -0.68
    áctica
    -0.68
     respeito
    -0.67
    POSITIVE LOGITS
     EdgeInsets
    1.91
    ::_('
    0.89
    EdgeInsets
    0.89
     médié
    0.88
    维度
    0.79
    contentPadding
    0.78
    Symmetric
    0.78
     asymmetrical
    0.76
    setPadding
    0.76
     const
    0.75
    Activations Density 0.001%

    No Known Activations