© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 33290
    Prev
    Next
    INDEX
    Explanations

    allergy and allergic reactions

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

    medical and scientific terminology related to allergies, particularly allergic rhinitis and immunological conditions.

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

    This neuron is highly sensitive to mentions of allergic rhinitis (e.g. “allergic rhin-” and “itis”).

    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
     analgesic
    -0.85
     Appetite
    -0.77
     syphilis
    -0.77
     neoplas
    -0.75
     bruises
    -0.74
    ὄ
    -0.73
     PSYCH
    -0.73
     ischemia
    -0.72
     insolvency
    -0.72
     Kula
    -0.72
    POSITIVE LOGITS
     allergy
    3.22
     allergic
    2.89
     allergies
    2.75
     Allergy
    2.73
     allergen
    2.61
     allergens
    2.55
    Aller
    2.53
    aller
    2.47
     aller
    2.45
     Aller
    2.45
    Activations Density 0.087%

    No Known Activations