© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 75011
    Prev
    Next
    INDEX
    Explanations

    programming and specific nouns

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

    The neuron is detecting numerical literals (numbers and numeric constants) in 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
    tront
    -1.03
     each
    -0.99
     fald
    -0.97
    ∷
    -0.96
     ſeveral
    -0.95
     farmacé
    -0.95
    虓
    -0.94
     maler
    -0.93
    ZIL
    -0.93
    hone
    -0.92
    POSITIVE LOGITS
     moderately
    1.08
     extraordinarily
    1.07
    رحلة
    1.06
     take
    1.05
    ocardi
    1.01
     transfer
    1.00
     profoundly
    1.00
    inkov
    0.99
     genuinely
    0.99
     give
    0.98
    Activations Density 0.002%

    No Known Activations