© 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. 59188
    Prev
    Next
    INDEX
    Explanations

    transparency and opacity

    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
    骉
    -1.52
     giúp
    -1.48
    ا
    -1.42
    对象
    -1.38
     Empfindung
    -1.37
    同じ
    -1.36
    -1.32
    闢
    -1.31
    ación
    -1.30
    فایل‌لار
    -1.29
    POSITIVE LOGITS
     you
    2.11
    她也
    1.32
     There
    1.32
     in
    1.31
    Libros
    1.29
    there
    1.28
     there
    1.25
    両方
    1.24
    好在
    1.24
    اريخ
    1.23
    Activations Density 0.090%

    No Known Activations