© 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. 10863
    Prev
    Next
    INDEX
    Explanations

    javascript function calls

    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
    a
    0.76
    bcc
    0.74
    mama
    0.73
    ாப்
    0.71
    ^{\#}\
    0.69
     $/
    0.69
    ую
    0.68
    Mama
    0.67
    magnitude
    0.67
    笉
    0.66
    POSITIVE LOGITS
    (){
    1.04
     Gobierno
    1.04
    Codigo
    0.90
     consiguió
    0.89
     समाधान
    0.88
     persönlichen
    0.87
     Wallpaper
    0.87
     Tudo
    0.86
    ({
    0.85
     आहार
    0.85
    Activations Density 0.010%

    No Known Activations