© 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. 56774
    Prev
    Next
    INDEX
    Explanations

    NAD and dehydrogenase cofactors

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

    biochemical molecules like NAD(P)H, enzymes, and chemical compounds in scientific texts.

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered by @neilrathi
    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
    acate
    -0.75
     berapa
    -0.72
    anlagen
    -0.71
     Landlord
    -0.69
     Policy
    -0.69
     eingestellt
    -0.68
     Shipped
    -0.68
     carbonate
    -0.67
     скачать
    -0.67
     مدير
    -0.67
    POSITIVE LOGITS
     NAD
    2.28
    NAD
    1.98
    FAD
    1.33
     Nad
    1.27
     cof
    1.25
     Coen
    1.19
    ADH
    1.10
    nad
    1.07
     nad
    1.06
    Nad
    1.01
    Activations Density 0.106%

    No Known Activations