© 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. 22-GEMMASCOPE-RES-131K
    4. 72482
    Prev
    Next
    INDEX
    Explanations

    chemical and physical processes

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

    chemical processing terms like "oxidation," "esterification," "dehydration," and other 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
    來的
    -1.33
    裡的
    -1.30
     acestea
    -1.29
    內的
    -1.27
     '\''
    -1.26
     empêcher
    -1.26
     Epson
    -1.25
     vardı
    -1.24
    有一個
    -1.23
     Infór
    -1.22
    POSITIVE LOGITS
     of
    3.50
     with
    1.95
     in
    1.84
     using
    1.68
     at
    1.65
     by
    1.65
     process
    1.49
     as
    1.41
     technique
    1.35
     procedure
    1.30
    Activations Density 0.186%

    No Known Activations