© 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. 3394
    Prev
    Next
    INDEX
    Explanations

    words following parentheses

    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
    o
    1.04
    ie
    1.03
    ’
    1.01
    <start_of_image>
    0.99
    ne
    0.96
    '
    0.96
    fl
    0.94
    var
    0.94
    -
    0.94
    de
    0.94
    POSITIVE LOGITS
     Revisited
    2.23
     Kết
    2.02
     Ecosystem
    2.01
     Terbaik
    1.97
     Chassis
    1.95
     Hệ
    1.94
     Tập
    1.94
     Multiplayer
    1.93
     Entrenamiento
    1.92
     Encryption
    1.92
    Activations Density 0.405%

    No Known Activations