© 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. 47723
    Prev
    Next
    INDEX
    Explanations

    metabolite and its products

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

    The neuron detects the word "metabolite" and its plural form "metabolites" in scientific or medical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    of
    -3.17
    ING
    -3.03
    。
    -3.02
    ',
    -2.98
    臯
    -2.86
    疍
    -2.69
    ।
    -2.52
    {
    -2.52
     problemy
    -2.48
    1
    -2.47
    POSITIVE LOGITS
    ’，
    2.98
    replyreport
    2.91
    ’
    2.64
     ‘
    2.47
     It
    2.38
    她说
    2.31
    ediakan
    2.30
    !”
    2.28
     inspiré
    2.28
     она
    2.27
    Activations Density 0.018%

    No Known Activations