© 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. 3495
    Prev
    Next
    INDEX
    Explanations

    .ing, "or", font

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

    The neuron fires on long spans of whitespace (especially large indentation or space‐only tokens).

    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
    zug
    -0.96
    RTSN
    -0.88
    tosa
    -0.85
     comportements
    -0.84
     Incluye
    -0.80
    azzo
    -0.79
    otipo
    -0.79
     colorado
    -0.78
     segurança
    -0.78
     sécurité
    -0.78
    POSITIVE LOGITS
    static
    1.24
     so
    0.91
     static
    0.85
    Tá
    0.82
     notable
    0.80
    ⎧
    0.78
    Robots
    0.75
     as
    0.73
     {
    0.73
     {
    0.71
    Activations Density 0.001%

    No Known Activations