© 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. 64896
    Prev
    Next
    INDEX
    Explanations

    victory over score

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

    This neuron detects numeric references in sports contexts—especially game numbers, set/match counts, and score figures.

    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
    にとっては
    -0.92
     başlay
    -0.92
    Beispiel
    -0.91
     these
    -0.90
    けっこう
    -0.89
     yoox
    -0.88
     furo
    -0.86
     tranf
    -0.86
    čnih
    -0.85
    从此
    -0.85
    POSITIVE LOGITS
     hatal
    1.07
     isolada
    1.01
     werd
    1.01
    ๓
    0.98
     influenci
    0.97
     attempt
    0.96
    Harbor
    0.96
     on
    0.94
    cheibe
    0.93
     recentes
    0.93
    Activations Density 0.014%

    No Known Activations