© 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. 10-GEMMASCOPE-RES-131K
    7. 113049
    Prev
    Next
    INDEX
    Explanations

    canvas and window creation

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

    code related to graphical user interface (GUI) components, windows, and display properties.

    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
     utilizan
    -1.58
     podían
    -1.54
     podrían
    -1.52
     serán
    -1.46
    lccc
    -1.41
    他們
    -1.38
     necesitan
    -1.35
     mejoras
    -1.34
    也可以
    -1.33
     schwier
    -1.33
    POSITIVE LOGITS
     its
    1.63
     inexp
    1.32
    Its
    1.29
    เติ
    1.27
    ✂
    1.26
     it
    1.26
     so
    1.24
     pesta
    1.24
    feit
    1.23
     १
    1.23
    Activations Density 0.311%

    No Known Activations