© 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. 100024
    Prev
    Next
    INDEX
    Explanations

    plotting graphs and charts

    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
    滉
    -1.43
     EXCELL
    -1.39
    givers
    -1.38
     فقط
    -1.31
    ifying
    -1.31
    шена
    -1.28
    察觉
    -1.28
     είχε
    -1.28
     tine
    -1.27
    Caratteristiche
    -1.27
    POSITIVE LOGITS
    '
    1.78
    汌
    1.59
    </em>
    1.52
     results
    1.52
     și
    1.52
     our
    1.45
     outcomes
    1.34
     different
    1.32
     perdiendo
    1.30
    </strong>
    1.30
    Activations Density 0.102%

    No Known Activations