© 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. 34-GEMMASCOPE-RES-131K
    7. 65556
    Prev
    Next
    INDEX
    Explanations

    pain and related symptoms

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

    phrases related to pain, symptoms, and physical discomfort.

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

    The neuron selectively activates on mentions of pain and related clinical symptoms (e.g. tenderness, inflammation, swelling, stiffness) in medical or health‐related contexts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     pain
    -2.75
     paint
    -2.33
    pain
    -2.23
     paints
    -2.22
     Pain
    -2.08
    Pain
    -2.06
     Paints
    -2.00
     pains
    -1.98
     painting
    -1.94
    PAINT
    -1.94
    POSITIVE LOGITS
     stiffness
    0.82
    étisme
    0.79
    ੨
    0.75
     Brend
    0.75
    çası
    0.73
    薗
    0.71
     sculpture
    0.71
     Petal
    0.70
     Colbert
    0.69
     sculptor
    0.69
    Activations Density 0.037%

    No Known Activations