© 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. 10-GEMMASCOPE-RES-131K
    7. 83949
    Prev
    Next
    INDEX
    Explanations

    ascorbic acid and citrus

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

    mentions of vitamin C and ascorbic acid in nutritional and scientific 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
    8
    -1.34
    .):
    -1.28
    5
    -1.27
    uyer
    -1.27
    .)
    -1.23
     Tienen
    -1.23
     بهترین
    -1.18
     pervasive
    -1.17
    ettu
    -1.16
    匆匆
    -1.16
    POSITIVE LOGITS
    歘
    1.36
    鸶
    1.34
    鹟
    1.30
     facilité
    1.29
    arım
    1.26
     XXVI
    1.23
     resultat
    1.21
     épu
    1.20
     italiens
    1.19
     coute
    1.19
    Activations Density 0.042%

    No Known Activations