© 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. 31-GEMMASCOPE-2-RES-262K
    7. 10401
    Prev
    Next
    INDEX
    Explanations

    computer input devices and functions

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

    input devices and controls

    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_31_width_262k_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
    社會
    0.56
    autoarima
    0.55
    social
    0.54
    DATABASE
    0.53
    住宿
    0.53
    ANTED
    0.52
    jsonplaceholder
    0.50
    糧
    0.50
    itochond
    0.50
    conciliation
    0.49
    POSITIVE LOGITS
     Keyboard
    1.31
     keyboard
    1.27
     Joystick
    1.23
     Mouse
    1.17
    Keyboard
    1.16
     joystick
    1.16
    鼠标
    1.14
     mouse
    1.12
     teclado
    1.08
     touchpad
    1.05
    Activations Density 0.155%

    No Known Activations