© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 58805
    Prev
    Next
    INDEX
    Explanations

    enzyme catalysis and activity

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

    biochemical enzyme information, particularly when discussing catalytic activity, EC classifications, and enzyme function.

    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
     EconPapers
    -1.35
     plantea
    -1.34
     eher
    -1.29
    桫
    -1.28
     culmin
    -1.28
    uminum
    -1.28
    戋
    -1.27
     joga
    -1.27
     概要
    -1.27
    ArgsConstructor
    -1.27
    POSITIVE LOGITS
    }$.
    1.86
     or
    1.59
    What
    1.46
    ウ
    1.36
     such
    1.34
    Some
    1.34
    目錄
    1.34
    How
    1.34
    With
    1.32
     กับ
    1.29
    Activations Density 0.298%

    No Known Activations