© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 33742
    Prev
    Next
    INDEX
    Explanations

    nutritional supplements and related compounds

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

    words related to dietary supplements and nutritional products.

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

    The main thing this neuron does is detect mentions of dietary supplements and related nutritional-supplement terminology.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     tronic
    -1.20
    徒歩
    -1.20
    createNewFile
    -1.19
     aplicable
    -1.18
    頜
    -1.17
    💬
    -1.16
    latLng
    -1.13
    国道
    -1.13
     وزير
    -1.13
     dollari
    -1.11
    POSITIVE LOGITS
     ویتامین
    1.49
     containing
    1.45
     cukru
    1.42
    lojik
    1.30
    鱉
    1.27
     dégust
    1.27
    кспер
    1.26
     ráp
    1.26
    Źródło
    1.24
     витами
    1.24
    Activations Density 0.065%

    No Known Activations