© 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. 98762
    Prev
    Next
    INDEX
    Explanations

    sporadic issues with diseases

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

    The neuron identifies and activates for the word "sporadic" when used in scientific and medical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered by @neilrathi
    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
    y
    -3.23
    埽
    -2.83
    ?"
    -2.66
    デュー
    -2.55
     soñ
    -2.45
    でに
    -2.34
    であった
    -2.31
    籥
    -2.31
    used
    -2.27
    section
    -2.22
    POSITIVE LOGITS
     unangemess
    2.81
     speziellen
    2.73
    .
    2.70
     unmittel
    2.69
     vollständ
    2.69
     zusätz
    2.67
    meteries
    2.61
     attaining
    2.55
    –
    2.47
     täglichen
    2.44
    Activations Density 0.002%

    No Known Activations