© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 90439
    Prev
    Next
    INDEX
    Explanations

    game boards

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

    This neuron responds to code‐style tokens—namely uppercase identifiers and numeric literals (e.g. array indices, constants, all-caps names, and digits).

    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
     Wirtschaft
    -0.78
    Question
    -0.78
    tea
    -0.75
     piani
    -0.72
     Opiniones
    -0.71
    ∮
    -0.71
    🥙
    -0.70
    葡萄
    -0.70
     tables
    -0.69
     there
    -0.69
    POSITIVE LOGITS
     Tic
    0.90
     winning
    0.89
     Winning
    0.84
     VIN
    0.79
     WIN
    0.78
    Winning
    0.77
     MOL
    0.77
     winnings
    0.75
    игры
    0.73
     win
    0.73
    Activations Density 0.010%

    No Known Activations