© 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. 16091
    Prev
    Next
    INDEX
    Explanations

    game end statistics

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

    This neuron detects detailed play-by-play sports action descriptions, especially baseball pitching and fielding event verbs.

    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
    Manfaat
    -1.01
    这些
    -0.94
     musíte
    -0.94
    OBJETIVOS
    -0.91
     maail
    -0.91
     instituições
    -0.91
     their
    -0.88
    .}(
    -0.86
    Banyak
    -0.86
    它们
    -0.86
    POSITIVE LOGITS
     войск
    1.06
    nextProps
    0.99
    writerow
    0.99
     sequential
    0.98
     minY
    0.97
    drawSprites
    0.96
    ⟩
    0.94
    絝
    0.94
    getMenuInflater
    0.94
     DRAWINGS
    0.94
    Activations Density 0.004%

    No Known Activations