© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 35168
    Prev
    Next
    INDEX
    Explanations

    button press actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    賁
    0.39
     掛
    0.39
    clicks
    0.38
    ⢸
    0.38
    Mus
    0.38
    offs
    0.38
    Substituting
    0.38
     clickable
    0.37
    mus
    0.37
     ব্যবহারের
    0.36
    POSITIVE LOGITS
    pressed
    0.75
     presses
    0.72
     pressed
    0.71
     Pressed
    0.70
     Press
    0.69
    押
    0.67
     pressing
    0.66
    Pressed
    0.63
     PRESS
    0.62
    Press
    0.61
    Activations Density 0.000%

    No Known Activations