© 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. 60737
    Prev
    Next
    INDEX
    Explanations

    characters in quotes or parentheses

    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
     peruana
    -1.88
    ied
    -1.68
     that
    -1.64
    墙壁
    -1.62
    元々
    -1.62
    ometries
    -1.61
    箆
    -1.60
    もともと
    -1.59
    cel
    -1.59
    withCredentials
    -1.58
    POSITIVE LOGITS
     '[
    1.71
    หลาย
    1.66
     '
    1.65
    ان
    1.63
    actéristi
    1.52
    )
    1.52
     zarówno
    1.52
    $,
    1.47
     więc
    1.44
     vali
    1.44
    Activations Density 0.019%

    No Known Activations