© 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. 34-GEMMASCOPE-RES-131K
    7. 3152
    Prev
    Next
    INDEX
    Explanations

    bowling or bowls

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

    The neuron activates on specialized sports terminology (e.g. names and jargon associated with a particular game like “crown green bowls”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ofan
    -0.71
     Wulf
    -0.71
     pulp
    -0.70
    тол
    -0.68
     通り
    -0.65
    wolves
    -0.65
     film
    -0.64
    podcast
    -0.63
    urator
    -0.63
     From
    -0.62
    POSITIVE LOGITS
     Bowls
    1.71
     bowlers
    1.59
     bowls
    1.52
     bowling
    1.30
     bowler
    1.20
     rink
    1.09
     Bowling
    1.06
     lawn
    1.04
    Bow
    0.96
    bowling
    0.94
    Activations Density 0.009%

    No Known Activations