© 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. 83788
    Prev
    Next
    INDEX
    Explanations

    version numbers, file extensions, and dates

    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
    Cheque
    -0.72
    嬰兒
    -0.69
     kèm
    -0.68
    镑
    -0.65
    anej
    -0.64
    ικα
    -0.63
    NST
    -0.63
     Operators
    -0.62
     Diplomat
    -0.62
    Operators
    -0.60
    POSITIVE LOGITS
    chr
    0.71
     Nose
    0.71
    setup
    0.69
    DEV
    0.69
     Hour
    0.68
     Corey
    0.68
    sequelize
    0.67
    デル
    0.67
     nog
    0.65
    yati
    0.65
    Activations Density 0.055%

    No Known Activations