© 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-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 115850
    Prev
    Next
    INDEX
    Explanations

    HTML tags and attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     diğer
    -0.07
     এতে
    -0.07
     çünkü
    -0.06
     др
    -0.06
     других
    -0.06
    其它
    -0.06
     rabbi
    -0.06
     removes
    -0.06
    ほか
    -0.06
     nhiều
    -0.06
    POSITIVE LOGITS
     допъл
    0.07
     freaking
    0.06
     vielä
    0.06
    ↵↵
    0.06
     гораздо
    0.06
    까지
    0.06
    といえば
    0.06
    まで
    0.05
     वेतन
    0.05
     まで
    0.05
    Activations Density 0.002%

    No Known Activations