© 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. 58130
    Prev
    Next
    INDEX
    Explanations

    division and numbers

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

    The neuron responds to single‐character numeric tokens (individual digits) in the text.

    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
     or
    -1.70
    ★★★★
    -1.65
    月は
    -1.64
    utiva
    -1.62
    ★★★★★
    -1.62
    ★★★
    -1.59
     Dinamarca
    -1.57
     responder
    -1.56
    ьет
    -1.55
    犇
    -1.55
    POSITIVE LOGITS
    ↵↵↵
    1.75
    .
    1.69
    1.64
     dergleichen
    1.63
    1
    1.62
     first
    1.58
     verwende
    1.55
     \
    1.51
     gleichen
    1.48
    榦
    1.47
    Activations Density 0.026%

    No Known Activations