© 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. 10197
    Prev
    Next
    INDEX
    Explanations

    Olympics, Creek, league, Special Olympics, minor league, Cherry Creek

    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
     there
    -1.74
    d
    -1.52
     in
    -1.51
    骤
    -1.51
    er
    -1.48
    %
    -1.48
    t
    -1.47
    There
    -1.44
    ong
    -1.42
    m
    -1.42
    POSITIVE LOGITS
    栒
    1.75
     pracuje
    1.75
    皛
    1.70
    尨
    1.67
    姽
    1.64
    厹
    1.63
     réellement
    1.61
    訁
    1.61
     experi
    1.56
     ใหม่
    1.56
    Activations Density 0.070%

    No Known Activations