© 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. 62818
    Prev
    Next
    INDEX
    Explanations

    chess tournament placings and titles

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

    The neuron strongly activates on proper names and key biographical descriptors (titles, roles, achievements) in chess‐player biography texts.

    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
    ﷲ
    -1.23
    >|</
    -0.98
    FY
    -0.97
    Agency
    -0.94
     campus
    -0.93
     agency
    -0.93
    ческий
    -0.91
     iti
    -0.86
    .~\
    -0.85
    campus
    -0.84
    POSITIVE LOGITS
     chess
    1.62
     playing
    1.38
     opponents
    1.36
     tournament
    1.31
     Chess
    1.27
     torne
    1.24
     opponent
    1.23
     tournaments
    1.16
    chess
    1.14
     players
    1.07
    Activations Density 0.028%

    No Known Activations