© 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. 56767
    Prev
    Next
    INDEX
    Explanations

    exercise and muscle activity

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

    scientific terms and measurements related to exercise physiology research.

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered by @neilrathi

    The neuron fires on numeric tokens representing quantitative measurements (e.g., digits, counts, durations).

    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
     Fitness
    -0.89
     Vers
    -0.84
     Pay
    -0.82
     Cardiovascular
    -0.82
    ACTIVITY
    -0.78
     fitness
    -0.77
    injury
    -0.76
    fitness
    -0.75
     Past
    -0.75
    ম
    -0.74
    POSITIVE LOGITS
    rouwen
    0.80
    ിക
    0.80
     disinfection
    0.72
     elbow
    0.71
     volant
    0.71
    opoly
    0.70
    voli
    0.70
     Spiro
    0.69
    Hul
    0.69
    ził
    0.68
    Activations Density 0.152%

    No Known Activations