© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15878
    Prev
    Next
    INDEX
    Explanations

    allergy or allergic reaction

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

    The neuron is sensitive to mentions of allergens, irritants, or related health‐hazard exposures (e.g., mold, pollen, dust, allergies, asthma).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ランプ
    0.55
     stagnation
    0.55
    썬
    0.55
    ビリ
    0.55
    ixir
    0.53
     нрав
    0.53
    শী
    0.52
     policewomen
    0.52
     స్టార్
    0.51
     석
    0.50
    POSITIVE LOGITS
     allergy
    2.98
     allergen
    2.94
     allerg
    2.83
     allergic
    2.78
     allergens
    2.77
     Allerg
    2.77
     allergies
    2.75
     Allergy
    2.75
     аллер
    2.69
     alerg
    2.59
    Activations Density 0.223%

    No Known Activations