© 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. 129955
    Prev
    Next
    INDEX
    Explanations

    successfully used

    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
     such
    -1.55
    ↵↵↵↵↵↵↵
    -1.38
     could
    -1.29
    虔
    -1.27
    /
    -1.24
    ;
    -1.24
    ↵↵↵↵↵
    -1.23
     üz
    -1.22
    他又
    -1.22
     who
    -1.21
    POSITIVE LOGITS
     一个
    1.51
    Basically
    1.40
     الأخرى
    1.37
     schönes
    1.35
    before
    1.34
     詩
    1.34
    itsubishi
    1.33
    ございました
    1.32
    About
    1.32
     للق
    1.31
    Activations Density 0.033%

    No Known Activations