© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13082
    Prev
    Next
    INDEX
    Explanations

    catalyzes

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

    words related to enzyme catalytic activity, particularly the word "catalyzes" and its variations.

    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
     outras
    -2.78
    铊
    -2.73
     ideally
    -2.70
    其他
    -2.63
     widen
    -2.61
     of
    -2.53
     otras
    -2.42
     confident
    -2.41
     Their
    -2.39
     likewise
    -2.39
    POSITIVE LOGITS
    *
    3.25
    '
    2.70
    sandalia
    2.70
     estadounid
    2.58
    ...
    2.55
    
    2.53
    Ꮘ
    2.50
    魮
    2.42
     Badan
    2.39
    訁
    2.38
    Activations Density 0.007%

    No Known Activations