© 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. 75600
    Prev
    Next
    INDEX
    Explanations

    macro and micro nutrients

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

    words related to nutrition, especially micronutrients and dietary elements.

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

    This neuron detects mentions of nutritional status and nutrient deficiencies (e.g. macro- and micronutrient terms and deficiency).

    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
    atha
    -0.82
     capítulo
    -0.77
    ratory
    -0.76
    ologie
    -0.76
    +=(
    -0.75
     versos
    -0.75
    /}
    -0.74
    文本
    -0.73
    uers
    -0.73
     dầu
    -0.72
    POSITIVE LOGITS
     nutrients
    4.06
     nutrient
    3.55
    nutri
    3.17
     nutritional
    3.02
     Nutrients
    2.97
     Nutrient
    2.91
     nutrition
    2.83
     nutrientes
    2.58
    Nutrient
    2.55
    Nutri
    2.48
    Activations Density 0.055%

    No Known Activations