© 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. 10-GEMMASCOPE-RES-131K
    7. 6778
    Prev
    Next
    INDEX
    Explanations

    code blocks or object literals

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

    The neuron activates on numeric literal tokens (number constants) in 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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    o
    -1.83
     for
    -1.71
     by
    -1.61
     believes
    -1.61
     with
    -1.60
    d
    -1.55
     also
    -1.55
     at
    -1.54
     will
    -1.52
    ↵
    -1.48
    POSITIVE LOGITS
     nové
    1.92
     nowych
    1.92
    ㋛
    1.80
     nieuwe
    1.75
     nový
    1.72
     nowego
    1.70
    
    1.70
     peculiarly
    1.69
    ༛
    1.68
    𓆏
    1.68
    Activations Density 0.034%

    No Known Activations