© 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. 22-GEMMASCOPE-2-RES-16K
    7. 3287
    Prev
    Next
    INDEX
    Explanations

    circle and round

    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_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    컥
    1.06
    ियल
    1.01
    گاه
    0.95
     Qxd
    0.95
     diving
    0.92
    တွ
    0.92
     Explos
    0.90
     sko
    0.90
     불구하고
    0.89
    लों
    0.88
    POSITIVE LOGITS
    abouts
    1.75
     circumference
    1.57
    圈
    1.33
     clockwise
    1.32
     omkring
    1.29
    radius
    1.27
    arounds
    1.27
     edges
    1.26
    محمد
    1.24
     radius
    1.24
    Activations Density 0.158%

    No Known Activations