© 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. 34-GEMMASCOPE-RES-131K
    7. 98926
    Prev
    Next
    INDEX
    Explanations

    mouse pointer and cursor actions

    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
     suffic
    -0.79
     feminists
    -0.77
     Wra
    -0.77
     อา
    -0.73
     Anreg
    -0.71
     fixture
    -0.71
    annels
    -0.70
     wrappers
    -0.70
    ця
    -0.70
    UIControlState
    -0.70
    POSITIVE LOGITS
    pointer
    1.05
    move
    0.92
     pointer
    0.88
     Wait
    0.87
     move
    0.86
     MOVE
    0.86
     Move
    0.84
     grab
    0.83
    url
    0.82
     Hand
    0.81
    Activations Density 0.009%

    No Known Activations