© 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. 58235
    Prev
    Next
    INDEX
    Explanations

    medical problems

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

    medical or health-related problems and issues in descriptive texts.

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

    This neuron activates on nouns that denote health problems or medical conditions (e.g., “issues,” “problems,” “diseases,” “conditions”).

    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
    {...
    -1.66
     methode
    -1.46
    😌
    -1.45
     kapp
    -1.42
     to
    -1.40
    <td>
    -1.39
     kili
    -1.38
    😋
    -1.37
    🤩
    -1.36
     on
    -1.34
    POSITIVE LOGITS
    niosek
    1.42
     princesas
    1.39
     Geschwindigkeit
    1.38
    生活中
    1.36
    </strong>
    1.35
     verdades
    1.34
     cielos
    1.32
     inicios
    1.32
     моя
    1.30
     mesmas
    1.29
    Activations Density 0.059%

    No Known Activations