© 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-262K
    7. 5900
    Prev
    Next
    INDEX
    Explanations

    programming definitions and parameters

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    -/
    1.11
     &/
    1.07
    やお
    1.00
    いたり
    0.99
     seguintes
    0.96
    したり
    0.95
     افرادی
    0.94
    或其他
    0.94
     aquellas
    0.93
    /...
    0.92
    POSITIVE LOGITS
    only
    0.89
     only
    0.87
     Explained
    0.76
     With
    0.74
     Only
    0.74
     with
    0.71
     Instead
    0.71
    Only
    0.71
     instead
    0.71
    OK
    0.69
    Activations Density 0.065%

    No Known Activations