© 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. 15495
    Prev
    Next
    INDEX
    Explanations

    enzymes like dehydrogenase and oxidase

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

    The neuron detects biochemical enzyme names and their components, particularly focusing on phosphate dehydrogenase, NADPH, and other related 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
    _
    -1.31
    </i>
    -1.27
    ッカ
    -1.16
    甍
    -1.08
    AFFIRMED
    -1.08
    밋
    -1.07
     effetto
    -1.05
     negotiated
    -1.04
    anos
    -1.04
     pentru
    -1.04
    POSITIVE LOGITS
     подготов
    1.33
     και
    1.32
     و
    1.29
     этим
    1.29
     tím
    1.27
    </h2>
    1.21
    antado
    1.21
    sistencia
    1.20
    rieux
    1.20
     be
    1.20
    Activations Density 0.056%

    No Known Activations