© 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. 34-GEMMASCOPE-RES-131K
    7. 84227
    Prev
    Next
    INDEX
    Explanations

    programming code and loops

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

    This neuron activates on numeric literals (sequences of digits) 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_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
    봄
    -0.79
     loud
    -0.77
    èze
    -0.73
     lipat
    -0.73
    regas
    -0.73
     witnessing
    -0.72
    лят
    -0.72
     écoute
    -0.72
    สาร
    -0.72
    agog
    -0.72
    POSITIVE LOGITS
     ($
    1.38
    ($
    1.05
    bc
    1.04
     mt
    1.04
     $
    0.94
    mt
    0.90
     bc
    0.89
    似た
    0.88
     (($
    0.86
    pow
    0.84
    Activations Density 0.013%

    No Known Activations