© 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. 79356
    Prev
    Next
    INDEX
    Explanations

    special characters and abbreviations

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

    The neuron fires on numeric and related symbolic tokens (e.g. digits, equation symbols, and math‐style terms), marking out mathematical/scientific formulae.

    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
    बाह
    -0.75
    cda
    -0.73
     Aside
    -0.72
    tbx
    -0.71
    modity
    -0.70
     verdienen
    -0.70
    وروب
    -0.69
    шные
    -0.69
     desmotiv
    -0.69
    gint
    -0.68
    POSITIVE LOGITS
    icism
    0.98
     emerg
    0.91
     AROUND
    0.88
     Jharkhand
    0.87
     '(
    0.86
    ements
    0.85
    ksu
    0.84
     forem
    0.84
     toch
    0.80
     voer
    0.80
    Activations Density 0.000%

    No Known Activations