© 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. 8934
    Prev
    Next
    INDEX
    Explanations

    the idea is

    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
     in
    -2.03
     for
    -1.87
     вернуться
    -1.38
     sœur
    -1.34
     his
    -1.30
     a
    -1.28
     سایر
    -1.27
     and
    -1.22
     andere
    -1.21
     使っ
    -1.21
    POSITIVE LOGITS
    .“
    1.37
    ￮
    1.31
    ات
    1.29
    ilitatea
    1.27
    zember
    1.27
    "));
    1.27
    有沒有
    1.27
    还不错
    1.27
     Piala
    1.24
    rifugal
    1.24
    Activations Density 0.027%

    No Known Activations