© 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. 90661
    Prev
    Next
    INDEX
    Explanations

    drug and medical information

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

    medical and pharmaceutical information in drug references or documentation.

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

    This neuron fires on text that presents drug‐ or medication‐related reference information—headings and instructions like drug information lookup, pill identification, dosage, interactions, side effects, administration, etc.

    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
    REVISTA
    -0.84
    clairage
    -0.82
    UserName
    -0.79
    tsen
    -0.77
     revo
    -0.77
     Bourbon
    -0.76
    Тарих
    -0.75
    Chili
    -0.74
    giatan
    -0.74
     באתר
    -0.74
    POSITIVE LOGITS
     FDA
    0.97
    NDC
    0.81
     manufacturer
    0.80
    不管
    0.80
     scored
    0.79
     drug
    0.79
     score
    0.79
    Ive
    0.77
    may
    0.77
     عليك
    0.77
    Activations Density 0.008%

    No Known Activations