© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66791
    Prev
    Next
    INDEX
    Explanations

    billiard table games

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

    The neuron is responsive to mentions of sports and game names (e.g. cue games like snooker and pool, racket sports like squash, pinball, billiards, etc.).

    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
     札幌
    -1.59
    雠
    -1.58
    神
    -1.54
    襌
    -1.53
    餍
    -1.51
    ⢌
    -1.46
    蹀
    -1.45
    鐗
    -1.43
     العالمي
    -1.42
    騭
    -1.42
    POSITIVE LOGITS
    .
    2.00
    ne
    1.65
    se
    1.55
    m
    1.52
    v
    1.52
    r
    1.50
     ALL
    1.49
    i
    1.41
    s
    1.41
    n
    1.40
    Activations Density 0.002%

    No Known Activations