© 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. 21658
    Prev
    Next
    INDEX
    Explanations

    numbers and abbreviations

    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
    
    -2.14
    鸲
    -2.13
     Quando
    -2.13
    ⮑
    -2.13
     简介
    -2.02
    戋
    -1.99
     Функ
    -1.98
    ⎔
    -1.97
    蛲
    -1.93
    蟥
    -1.91
    POSITIVE LOGITS
     but
    2.67
     and
    2.45
     although
    2.16
     an
    2.00
     notable
    1.99
     five
    1.97
     with
    1.95
     additional
    1.94
     even
    1.93
     a
    1.92
    Activations Density 0.010%

    No Known Activations