© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 56863
    Prev
    Next
    INDEX
    Explanations

    code punctuation and symbols

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

    The neuron reliably activates on numeric literals in source code.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    運行
    -0.90
     easy
    -0.85
    Ond
    -0.83
    Lua
    -0.81
    Jonas
    -0.76
    ṓ
    -0.75
     Mahar
    -0.74
    kost
    -0.74
    Sera
    -0.74
    Diem
    -0.72
    POSITIVE LOGITS
    String
    0.91
     String
    0.89
    yard
    0.85
     равен
    0.79
     devenue
    0.77
     прав
    0.77
    pendenti
    0.76
     vroe
    0.74
     下着
    0.73
    cession
    0.72
    Activations Density 0.031%

    No Known Activations