Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8430
    Prev
    Next
    INDEX
    Explanations

    anticholinergic drugs

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

    This neuron detects pharmaceutical drug names and chemical compounds, particularly anticholinergic drugs like atropine and hyoscine.

    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
    alos
    -0.71
    Basics
    -0.69
    ازه
    -0.69
    ヴァ
    -0.67
    monial
    -0.67
    triangleq
    -0.66
    īts
    -0.66
    untungan
    -0.65
    forma
    -0.65
     wünsche
    -0.65
    POSITIVE LOGITS
     atrop
    1.58
     scopo
    1.22
    timus
    1.15
     acetylcholine
    1.05
     drying
    1.05
    Drying
    0.93
    drying
    0.92
     chol
    0.91
     dries
    0.90
     mus
    0.82
    Activations Density 0.069%

    No Known Activations