© 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. 22-GEMMASCOPE-RES-131K
    7. 72538
    Prev
    Next
    INDEX
    Explanations

    programming language keywords

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

    The neuron activates on numeric literals (e.g. integers or floating‐point constants) in the code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    Not in Any Lists

    No Comments

    Negative Logits
     rabat
    -1.05
     zimowa
    -1.02
     partic
    -1.01
     самостоятельно
    -0.98
    ử
    -0.97
     exogenous
    -0.97
     Dienstag
    -0.96
     postale
    -0.95
     strtolower
    -0.95
    rawd
    -0.94
    POSITIVE LOGITS
    却
    1.05
     these
    0.98
     that
    0.95
     can
    0.94
    場は
    0.93
     every
    0.90
    相应的
    0.90
     his
    0.88
     genannten
    0.88
     supper
    0.86
    Activations Density 0.005%

    No Known Activations