© 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. 22-GEMMASCOPE-RES-131K
    7. 127661
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on numeric expressions (digits, counts, measures, percentages) in the text.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408

    asking for clarification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     finestra
    -0.86
    äd
    -0.82
    Mvh
    -0.81
    자인
    -0.81
     Middlesbrough
    -0.78
     capitalize
    -0.78
     sitios
    -0.77
     Sleeps
    -0.76
     Conclu
    -0.76
    cipitation
    -0.76
    POSITIVE LOGITS
     what
    1.31
     Whatever
    0.96
    What
    0.94
    köy
    0.90
     whatever
    0.90
    Whatever
    0.87
     choice
    0.87
     mostly
    0.86
     What
    0.85
    是什么
    0.85
    Activations Density 0.124%

    No Known Activations