© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 56770
    Prev
    Next
    INDEX
    Explanations

    ascorbic acid

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

    The neuron detects references to ascorbic acid (vitamin C) and its derivatives in scientific contexts.

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

    The neuron is tuned to detect mentions of ascorbic acid (vitamin C) and closely related transporter terms.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     Ibarra
    -0.79
    unción
    -0.79
     Knudsen
    -0.77
     pétrole
    -0.71
    received
    -0.70
    Language
    -0.70
     Kund
    -0.70
    matric
    -0.69
    GraphQL
    -0.69
    Cincinnati
    -0.68
    POSITIVE LOGITS
     ascorbic
    1.41
     scur
    1.27
     Vitamin
    1.25
    Vitamin
    1.23
    🍊
    1.14
     vitamin
    1.11
     acero
    1.02
     kiwi
    0.96
     Linus
    0.94
     ویتامین
    0.94
    Activations Density 0.028%

    No Known Activations