© 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-65K
    7. 8740
    Prev
    Next
    INDEX
    Explanations

    logging.basicConfig format parameter

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    くて
    0.74
    <h3>
    0.68
     gifted
    0.65
     ক্লিক
    0.64
    되어
    0.64
    Peace
    0.64
     irrég
    0.63
    <h4>
    0.62
     giriş
    0.61
     quốc
    0.61
    POSITIVE LOGITS
     Assembl
    0.66
     Bells
    0.65
     Falcon
    0.64
     entend
    0.60
     Bert
    0.60
     সপ্তাহের
    0.60
     Arduino
    0.60
    ाना
    0.59
     Libert
    0.59
    Cab
    0.59
    Activations Density 0.001%

    No Known Activations