© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11522
    Prev
    Next
    INDEX
    Explanations

    basketball and NBA

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

    The neuron fires on the presence of named entities—especially capitalized names of people, teams, and places.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    🍄
    0.62
     Hew
    0.56
     Football
    0.56
    luoromethyl
    0.55
     neurologist
    0.55
    matchCondition
    0.53
    퓸
    0.53
    Football
    0.52
    HMS
    0.52
     weatherproof
    0.52
    POSITIVE LOGITS
     basketball
    2.22
     NBA
    2.19
     Basketball
    2.17
    Basketball
    2.14
     баскет
    2.09
    basketball
    2.06
    🏀
    2.03
    NBA
    1.97
     basket
    1.95
     баскетбол
    1.93
    Activations Density 0.284%

    No Known Activations