© 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. 82468
    Prev
    Next
    INDEX
    Explanations

    baseball walks

    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
    Radians
    -0.73
     Auff
    -0.69
    туаль
    -0.69
    solr
    -0.69
    РА
    -0.69
     Gartner
    -0.68
    ссажи
    -0.67
     дюй
    -0.67
    ächt
    -0.67
    рку
    -0.66
    POSITIVE LOGITS
     walks
    3.63
     walk
    3.47
     walking
    3.20
     walked
    2.97
    walk
    2.91
     Walk
    2.77
    walks
    2.69
     Walks
    2.67
     WALK
    2.59
     Walking
    2.56
    Activations Density 0.009%

    No Known Activations