© 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. 75962
    Prev
    Next
    INDEX
    Explanations

    dietary nutrition

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

    references to nutrition, dietitians, and dietary research.

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

    The neuron strongly activates on numeric tokens and bibliography‐style metadata (years, citation numbers, and other digits).

    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
    рѣ
    -0.91
    findpost
    -0.91
     FedEx
    -0.89
    opropyl
    -0.89
     Electronics
    -0.86
     Cowper
    -0.85
    ტი
    -0.84
     futbol
    -0.84
     hydrocarbons
    -0.83
     productId
    -0.83
    POSITIVE LOGITS
     nutrition
    3.44
     nutritional
    2.84
     Nutrition
    2.72
    Nutrition
    2.58
     dietary
    2.53
    nutrition
    2.48
     food
    2.45
     diet
    2.34
     Nutritional
    2.11
     Dietary
    2.03
    Activations Density 0.194%

    No Known Activations