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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 1801
    Prev
    Next
    INDEX
    Explanations

    sickness and health conditions

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

    The neuron detects the word "sickness" and related terms for illnesses or medical conditions.

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

    The neuron consistently activates on occurrences of the word “sickness.”

    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
    盌
    -3.03
    ︕
    -2.88
    桖
    -2.86
    镦
    -2.84
    ↓↓↓
    -2.78
    ！"
    -2.75
    梣
    -2.73
    voyez
    -2.72
    🥳
    -2.66
     jokingly
    -2.64
    POSITIVE LOGITS
    .
    4.22
     MUCH
    2.69
    ↵
    2.56
     He
    2.52
    也不能
    2.44
    斟
    2.44
     jedes
    2.34
    䊐
    2.34
    要不然
    2.34
     allgeme
    2.33
    Activations Density 0.002%

    No Known Activations