© 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. 67448
    Prev
    Next
    INDEX
    Explanations

    WM, Eastwood, Elba, Constance

    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
    糨
    -3.00
     concentrado
    -2.92
    闼
    -2.88
    馓
    -2.86
    埸
    -2.81
     碗
    -2.81
     participado
    -2.75
    ઁ
    -2.72
    汌
    -2.69
    ⡰
    -2.67
    POSITIVE LOGITS
    n
    3.73
    ’
    3.50
    8
    3.47
    9
    3.27
    which
    3.14
     Whether
    3.14
    This
    3.09
     Quite
    3.05
    м
    3.02
    We
    2.98
    Activations Density 0.022%

    No Known Activations