© 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. 3600
    Prev
    Next
    INDEX
    Explanations

    `extends` or `defaultdict`

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

    The neuron fires on programming-language definitions—class/type declarations and initializer signatures (e.g. “class,” “extends,” “defaultdict,” init methods).

    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
     Thorne
    -0.72
    ्यू
    -0.69
    ratore
    -0.69
    ẖ
    -0.68
     huéspedes
    -0.66
     уче
    -0.65
     tenancy
    -0.65
    🛥
    -0.64
    dinger
    -0.64
     få
    -0.64
    POSITIVE LOGITS
     oble
    0.68
    setUp
    0.67
     Grafton
    0.66
     Luv
    0.65
    llium
    0.65
    englisch
    0.65
     保
    0.65
    вия
    0.64
     steamers
    0.64
     muscles
    0.63
    Activations Density 0.081%

    No Known Activations