© 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. 86490
    Prev
    Next
    INDEX
    Explanations

    graphics rendering and shader code

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     měla
    -1.62
    5
    -1.60
     miała
    -1.56
     gdyby
    -1.49
    bumptech
    -1.48
    禤
    -1.46
     powinna
    -1.46
    1
    -1.45
     wystarczy
    -1.39
     she
    -1.38
    POSITIVE LOGITS
    Framebuffer
    1.45
     we
    1.45
    ¡¡
    1.44
     conç
    1.41
     vives
    1.36
    нт
    1.36
    ¡¡¡
    1.36
    💬
    1.34
    efeated
    1.33
     Он
    1.30
    Activations Density 0.006%

    No Known Activations