© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 12234
    Prev
    Next
    INDEX
    Explanations

    google web toolkit

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

    references to Google Web Toolkit (GWT) and related web application framework terms.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     was
    -1.89
     are
    -1.89
     now
    -1.56
    )."
    -1.53
    the
    -1.53
    。"
    -1.50
     becomes
    -1.48
    )$;
    -1.46
    现在的
    -1.45
    艫
    -1.43
    POSITIVE LOGITS
    gwt
    1.84
    ずら
    1.63
     sicheren
    1.38
     insuper
    1.36
     you
    1.33
     swojej
    1.33
    velles
    1.30
    なかった
    1.30
     MIRROR
    1.27
     проєкту
    1.26
    Activations Density 0.012%

    No Known Activations