© 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. 34-GEMMASCOPE-RES-131K
    4. 37779
    Prev
    Next
    INDEX
    Explanations

    licensed under

    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
     Grow
    -0.79
     BM
    -0.77
     Portal
    -0.75
     tracker
    -0.70
    鎭
    -0.70
     AA
    -0.69
     CAP
    -0.69
     xs
    -0.68
     IS
    -0.68
    辈子
    -0.68
    POSITIVE LOGITS
     relazione
    0.77
    tableName
    0.75
    裄
    0.75
    aggregated
    0.71
    arithmetic
    0.71
     zmiany
    0.69
     conosce
    0.67
     réunis
    0.67
    vět
    0.66
     utilizza
    0.66
    Activations Density 0.041%

    No Known Activations