© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 127860
    Prev
    Next
    INDEX
    Explanations

    The neuron primarily detects references to games, especially video‐gaming terms.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408

    video games and gaming

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Negative Logits
    </sup>
    -1.24
     there
    -1.17
     materia
    -1.16
     procedures
    -1.12
    :"-
    -1.08
     observa
    -1.08
    andola
    -1.06
     arran
    -1.04
     bordering
    -1.04
     our
    -1.03
    POSITIVE LOGITS
     game
    1.81
     games
    1.67
    🎮
    1.47
    เกม
    1.45
    ⎔
    1.41
     gaming
    1.37
    ゲーム
    1.28
     खेल
    1.24
     franquicia
    1.23
    เล่น
    1.23
    Activations Density 0.080%

    No Known Activations