© 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. 10-GEMMASCOPE-RES-131K
    7. 7476
    Prev
    Next
    INDEX
    Explanations

    NADH, NADPH, NADP, NAD+

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

    This neuron detects variations of "NAD" (Nicotinamide Adenine Dinucleotide) and related biochemical compounds in 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
    ⁛
    -2.56
     môže
    -2.50
     pokud
    -2.50
    哢
    -2.42
    elerik
    -2.42
    椹
    -2.39
    %")
    -2.38
    
    -2.38
     Of
    -2.33
     możemy
    -2.33
    POSITIVE LOGITS
    s
    3.47
    ↵
    3.00
    能在
    2.63
    —
    2.55
    O
    2.38
    ‘
    2.36
     empower
    2.36
    In
    2.30
    H
    2.30
    A
    2.27
    Activations Density 0.003%

    No Known Activations