© 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. 22-GEMMASCOPE-RES-131K
    7. 74999
    Prev
    Next
    INDEX
    Explanations

    game, point, escape

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

    The neuron detects tennis match action and scoring terms (e.g. breaking serve, game, match point, ace).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     those
    -1.15
     who
    -1.05
     whose
    -1.03
    那些
    -1.01
     to
    -0.99
    erobic
    -0.98
    toluene
    -0.98
    🆕
    -0.94
     from
    -0.94
    tarte
    -0.94
    POSITIVE LOGITS
    的笑
    0.99
    USTER
    0.99
    米国
    0.97
     sostegno
    0.95
    …’
    0.95
    ércoles
    0.94
    Referințe
    0.94
    顱
    0.93
     this
    0.92
     kolejne
    0.92
    Activations Density 0.004%

    No Known Activations