© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13662
    Prev
    Next
    INDEX
    Explanations

    medical disorders

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

    medical and health-related disorders in scientific or technical contexts.

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

    This neuron specifically detects occurrences of the word “disorders.”

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    艽
    -3.16
    떳
    -2.94
    ſſen
    -2.91
    ндарт
    -2.88
     assiste
    -2.84
     interag
    -2.73
    effort
    -2.69
    луйста
    -2.67
    埽
    -2.66
    䛗
    -2.64
    POSITIVE LOGITS
    3
    4.13
    <i>
    3.45
    ↵↵
    3.03
    7
    3.00
      
    2.91
    9
    2.88
    .
    2.84
    4
    2.78
    ING
    2.77
    0
    2.73
    Activations Density 0.020%

    No Known Activations