© 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. 38811
    Prev
    Next
    INDEX
    Explanations

    double curly braces

    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
     espécies
    -1.77
    乄
    -1.59
    allergenic
    -1.54
     każdy
    -1.52
    zaSy
    -1.52
    owm
    -1.52
     Geografía
    -1.52
    leanor
    -1.51
    が付いて
    -1.50
    であろう
    -1.49
    POSITIVE LOGITS
    优点
    1.52
     cantik
    1.49
    我们的
    1.41
     &
    1.41
    hmig
    1.38
    Just
    1.37
     detayl
    1.36
    ཫ
    1.33
    饮料
    1.33
    param
    1.29
    Activations Density 0.068%

    No Known Activations