© 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. 6656
    Prev
    Next
    INDEX
    Explanations

    clinical manifestations

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

    The neuron detects the word "manifestations" in medical contexts, particularly when describing symptoms or presentations of diseases.

    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
    as
    -2.89
    B
    -2.66
    鯪
    -2.45
    n
    -2.33
    one
    -2.31
     הוא
    -2.25
    $
    -2.20
    Y
    -2.19
    M
    -2.09
    孓
    -2.08
    POSITIVE LOGITS
    眥
    2.66
     главным
    2.38
    各样的
    2.34
    лла
    2.23
     неболь
    2.23
     So
    2.19
    Referenties
    2.16
    ᡵ
    2.16
     collaborating
    2.09
     aparentemente
    2.08
    Activations Density 0.007%

    No Known Activations