© 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. 73557
    Prev
    Next
    INDEX
    Explanations

    play calling

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

    The neuron strongly activates on sports‐media and game‐coverage terms—words tied to play-by-play commentary, broadcaster names, team events, and related vocabulary.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    ágos
    -0.73
    getUser
    -0.73
    检查
    -0.69
    gini
    -0.67
     yawn
    -0.66
    ment
    -0.65
    反應
    -0.65
    𝕚
    -0.65
     concevoir
    -0.65
    âng
    -0.65
    POSITIVE LOGITS
     play
    2.63
    play
    2.00
    Play
    1.82
     calling
    1.59
     Play
    1.54
    calling
    1.53
     PLAY
    1.42
     call
    1.42
     calls
    1.40
     Calling
    1.38
    Activations Density 0.021%

    No Known Activations