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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 119046
    Prev
    Next
    INDEX
    Explanations

    medical symptoms

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

    This neuron identifies medical symptoms and conditions, particularly focusing on physical manifestations of illness like nausea, vomiting, pain, dizziness, and other clinical symptoms.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    Not in Any Lists

    No Comments

    Negative Logits
     of
    -1.11
    providedIn
    -1.00
    的人生
    -1.00
     by
    -0.96
     setempat
    -0.91
     to
    -0.91
     By
    -0.90
     mittlerweile
    -0.89
    ändert
    -0.89
     检测
    -0.89
    POSITIVE LOGITS
     or
    1.67
     یا
    1.33
    accompanied
    1.32
     accompagn
    1.28
     pouvant
    1.23
    trường
    1.19
     maleta
    1.17
     and
    1.17
     zlep
    1.14
    很赞
    1.11
    Activations Density 0.112%

    No Known Activations