© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15796
    Prev
    Next
    INDEX
    Explanations

    statistical leaders and scorers

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

    The neuron fires on numeric tokens and related words that denote sports statistics or performance figures (e.g. scores, counts, totals, and stat labels).

    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
     where
    -1.02
     evaluaciones
    -1.00
     to
    -0.99
     other
    -0.95
     very
    -0.92
    ťaž
    -0.92
     does
    -0.89
    Other
    -0.88
     now
    -0.86
     completely
    -0.86
    POSITIVE LOGITS
     industrie
    1.05
     salari
    1.04
    哚
    1.02
     parlement
    1.00
    デューサー
    1.00
    tait
    1.00
    鐧
    1.00
     plafon
    0.99
     consulte
    0.98
    ⡃
    0.97
    Activations Density 0.011%

    No Known Activations