© 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. 10-GEMMASCOPE-RES-131K
    7. 12574
    Prev
    Next
    INDEX
    Explanations

    sports teams

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

    The neuron spotlights mentions of sports teams and related roles (e.g. “team,” “players,” “manager,” “squad”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     /
    -1.53
    如此
    -1.51
    (!__
    -1.50
     كورة
    -1.48
    金
    -1.45
    rlpool
    -1.41
    四大
    -1.39
    セリ
    -1.38
    ."
    -1.36
     semble
    -1.36
    POSITIVE LOGITS
     to
    1.63
    錚
    1.47
    ⌗
    1.40
    憮
    1.39
     egenskaper
    1.39
     msec
    1.37
    tires
    1.36
     Geen
    1.35
     ;"
    1.34
    🎸
    1.34
    Activations Density 0.016%

    No Known Activations