© 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. 10-GEMMASCOPE-RES-131K
    7. 99768
    Prev
    Next
    INDEX
    Explanations

    on screen, stage, field, camera

    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_10/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
    ’
    -2.16
    .”
    -2.13
    {
    -1.91
     pedimos
    -1.88
    ሷ
    -1.86
    geſ
    -1.78
     より
    -1.77
    我们要
    -1.77
     (“
    -1.76
    鲞
    -1.75
    POSITIVE LOGITS
    浤
    2.16
    "
    2.08
     timeframe
    2.06
    ᠳ
    2.05
     accented
    2.02
    盌
    2.02
    厹
    2.02
     hordes
    1.97
     enthusiasm
    1.95
     appreci
    1.94
    Activations Density 0.023%

    No Known Activations