© 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. 34-GEMMASCOPE-RES-131K
    7. 30562
    Prev
    Next
    INDEX
    Explanations

    mouse actions and cursor

    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_34/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
    ider
    -0.77
    mirror
    -0.75
     onPostExecute
    -0.71
     Dur
    -0.71
    闢
    -0.71
    mona
    -0.69
     Мир
    -0.68
    सो
    -0.67
     Paleozoic
    -0.67
    ajar
    -0.66
    POSITIVE LOGITS
     mouse
    6.00
     Mouse
    4.50
    mouse
    4.44
    Mouse
    4.13
     mice
    4.13
    鼠标
    3.52
     MOUSE
    3.33
    MOUSE
    3.20
     murine
    3.03
     Mice
    3.02
    Activations Density 0.112%

    No Known Activations