© 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. 127920
    Prev
    Next
    INDEX
    Explanations

    function gets or CPU

    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
     ikke
    -0.09
     использования
    -0.08
     использует
    -0.06
     không
    -0.06
     verwendet
    -0.06
     не
    -0.06
     использовании
    -0.06
     использовать
    -0.06
     подготовке
    -0.06
     используют
    -0.06
    POSITIVE LOGITS
     පහ
    0.06
     bilingual
    0.06
    𝒍
    0.06
    hence
    0.05
     OBJECT
    0.05
     ২
    0.05
     প্রচারণা
    0.05
     सौदा
    0.05
    atth
    0.05
    aceut
    0.05
    Activations Density 0.001%

    No Known Activations