© 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. 7660
    Prev
    Next
    INDEX
    Explanations

    Judy and JUD-

    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
     mischievous
    -3.23
     extravagant
    -3.20
    ୌ
    -2.95
     exuberant
    -2.94
     cruel
    -2.89
    取締
    -2.83
     infamous
    -2.81
     sassy
    -2.78
     brutal
    -2.77
     clumsy
    -2.77
    POSITIVE LOGITS
    {
    3.23
    '
    3.11
    4
    3.02
    the
    2.97
     kelly
    2.95
    すっ
    2.86
     kulinar
    2.83
    1
    2.77
    鯪
    2.73
     広場
    2.72
    Activations Density 0.001%

    No Known Activations