© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 10153
    Prev
    Next
    INDEX
    Explanations

    task reminders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    этому
    0.92
    Started
    0.91
    Instit
    0.90
    usepackage
    0.88
    Outfit
    0.88
    ggle
    0.87
    CharSequence
    0.87
    Pierre
    0.85
    é
    0.85
     लगाएंगे
    0.85
    POSITIVE LOGITS
     month
    1.19
     repeated
    1.15
     week
    0.99
     months
    0.97
     defied
    0.96
     transduction
    0.93
    recipes
    0.92
     conflicting
    0.91
     twice
    0.91
     nighttime
    0.90
    Activations Density 0.001%

    No Known Activations