© 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. 10-GEMMASCOPE-RES-131K
    4. 118898
    Prev
    Next
    INDEX
    Explanations

    Aller and allergy-related words

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

    Words related to allergies and allergic reactions, particularly detecting terms like "allergen," "allergic," and "Allergan."

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

    The neuron selectively activates on words containing the “aller-” root (as in allergy, allergic, allergen, 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_10/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
    
    -3.28
    t
    -2.83
     обеспечения
    -2.50
    ’,
    -2.36
    es
    -2.36
    י
    -2.36
    媵
    -2.36
    on
    -2.25
    ’.”
    -2.22
    亹
    -2.20
    POSITIVE LOGITS
    0
    2.64
    ↵↵
    2.64
     wichtigen
    2.44
    tiques
    2.34
     beweisen
    2.30
    他没有
    2.22
    ⡪
    2.19
     Verständ
    2.13
     examinar
    2.08
     investigación
    2.06
    Activations Density 0.003%

    No Known Activations