© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 6721
    Prev
    Next
    INDEX
    Explanations

    dictionary or list containing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Play
    1.01
    xq
    0.93
     loadChildren
    0.93
     놀
    0.92
     reproducible
    0.91
    借助
    0.90
     removes
    0.90
     legais
    0.89
    lestage
    0.88
    '_{\
    0.88
    POSITIVE LOGITS
    gloss
    1.20
     balm
    1.07
    opolys
    1.06
    oxygenase
    1.04
    osomal
    0.99
     Balm
    0.95
    დი
    0.95
    ophilic
    0.94
    sticks
    0.93
     gloss
    0.92
    Activations Density 0.032%

    No Known Activations