© 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. 59954
    Prev
    Next
    INDEX
    Explanations

    nutritional supplements

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

    references to dietary or nutritional supplements.

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

    The main thing this neuron does is detect mentions of nutritional supplements (e.g., “supplements,” “supplemented,” “supplementation”).

    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
    шкина
    -1.72
     About
    -1.60
     kartun
    -1.56
     Even
    -1.55
    
    -1.50
     glän
    -1.49
    '
    -1.47
    }")
    -1.47
     envia
    -1.45
    ").
    -1.44
    POSITIVE LOGITS
    when
    1.83
     сайті
    1.63
    ↵↵
    1.59
    their
    1.56
     بدأ
    1.51
     cuando
    1.51
     quando
    1.48
     όταν
    1.45
    Hướng
    1.45
     loro
    1.45
    Activations Density 0.019%

    No Known Activations