© 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. 10-GEMMASCOPE-RES-131K
    7. 85223
    Prev
    Next
    INDEX
    Explanations

    nutrient status, cycling, or transformation

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

    The word "nutrient" or words closely related to nutrition in scientific contexts.

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

    The neuron activates on occurrences of the word “nutrient” (in any case).

    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
    1
    -3.30
    𐐪
    -2.70
     menyen
    -2.63
     teater
    -2.55
     slanted
    -2.53
     distrik
    -2.52
     Selecting
    -2.52
     Intense
    -2.52
     Descri
    -2.42
     dekoratif
    -2.42
    POSITIVE LOGITS
     Their
    2.73
    their
    2.64
    there
    2.59
    .
    2.44
     tries
    2.38
     THEIR
    2.36
     However
    2.34
    '
    2.34
    
    2.33
     contribute
    2.27
    Activations Density 0.004%

    No Known Activations