© 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. 111014
    Prev
    Next
    INDEX
    Explanations

    football actions and statistics

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects numeric sports performance statistics (e.g. yardage, receptions, catches, passes) in game summaries.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    ☫
    -1.66
     tige
    -1.59
    鹩
    -1.55
     nieuwe
    -1.51
     réve
    -1.50
     préférences
    -1.48
    SOBRE
    -1.48
     ſee
    -1.45
     coupe
    -1.45
     retours
    -1.45
    POSITIVE LOGITS
     to
    1.97
     that
    1.61
     then
    1.56
     was
    1.56
    re
    1.55
    u
    1.55
     people
    1.52
     only
    1.52
     four
    1.50
     takes
    1.49
    Activations Density 0.007%

    No Known Activations