© 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. 44805
    Prev
    Next
    INDEX
    Explanations

    gui elements

    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
    $
    -1.66
     basé
    -1.50
     aforementioned
    -1.33
    \
    -1.32
    一时间
    -1.29
     بسبب
    -1.29
    姈
    -1.27
     vary
    -1.26
    Y
    -1.25
     $
    -1.24
    POSITIVE LOGITS
     in
    2.11
     with
    1.92
     byste
    1.45
     You
    1.45
    epam
    1.45
    freundlich
    1.39
    umpulkan
    1.38
    ⃕
    1.37
    gangss
    1.35
    origami
    1.34
    Activations Density 0.006%

    No Known Activations