© 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. 104378
    Prev
    Next
    INDEX
    Explanations

    sports matches and games

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

    This neuron detects mentions of sports “match” headings or related terms (e.g. “match,” “matches,” “Friendly,” “qualifiers”) in the text.

    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
     firſt
    -1.38
     didn
    -1.36
    AutoresizingMask
    -1.33
    六年
    -1.31
    jemahan
    -1.30
     Autorizaciones
    -1.30
    ان
    -1.29
    的工作
    -1.29
    >
    -1.27
    五年
    -1.27
    POSITIVE LOGITS
     destinada
    1.32
    但她
    1.27
     dedicada
    1.23
    雰囲気が
    1.23
    𖥻
    1.23
    lana
    1.23
     merupakan
    1.23
     perdeu
    1.21
     ALLOC
    1.19
    瀰
    1.19
    Activations Density 0.035%

    No Known Activations