© 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. 22-GEMMASCOPE-RES-131K
    7. 15878
    Prev
    Next
    INDEX
    Explanations

    catalysts and supports

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

    terms related to catalysts and catalytic processes in chemical reactions.

    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_22/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
     three
    -1.11
    이의
    -1.09
     "/";
    -1.08
     lakier
    -1.08
     Its
    -1.07
     ".";
    -1.05
     They
    -1.05
    if
    -1.04
     "-";
    -1.04
    ie
    -1.02
    POSITIVE LOGITS
    Hô
    1.25
    傚
    1.20
     língua
    1.11
    哪儿
    1.08
    лению
    1.08
     cualquier
    1.08
     chimie
    1.08
     possessed
    1.07
     pensieri
    1.07
     trebui
    1.06
    Activations Density 0.158%

    No Known Activations