© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9180
    Prev
    Next
    INDEX
    Explanations

    mouse click and hold

    np_acts-logits-general · gemini-2.5-flash-lite

    pressing or clicking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WriteHeader
    0.51
     chambres
    0.41
    磵
    0.40
    ညီ
    0.40
    謄
    0.40
    лини
    0.39
    äle
    0.39
     फ्रिज
    0.39
    ਾਕ
    0.38
    鉀
    0.38
    POSITIVE LOGITS
     mouse
    1.75
     Mouse
    1.62
    mouse
    1.59
    Mouse
    1.59
    鼠标
    1.55
     click
    1.50
    click
    1.41
     drag
    1.39
    MouseDown
    1.38
     mouseDown
    1.38
    Activations Density 0.237%

    No Known Activations