© 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. 10-GEMMASCOPE-RES-131K
    7. 7107
    Prev
    Next
    INDEX
    Explanations

    bowling and related sports terms

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

    The neuron detects mentions of bowling or bowler (i.e., the word “bowling” and its close variants) in a sporting context.

    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
    独特
    -2.50
     hakk
    -2.47
    Of
    -2.31
    勠
    -2.25
    What
    -2.25
     honom
    -2.25
    This
    -2.23
    Its
    -2.22
    y
    -2.19
    Does
    -2.14
    POSITIVE LOGITS
    薷
    3.16
    the
    2.50
    心头
    2.34
    nées
    2.34
    螅
    2.31
    骉
    2.31
    縢
    2.30
    鍆
    2.23
    壜
    2.19
    炱
    2.17
    Activations Density 0.002%

    No Known Activations