© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 116024
    Prev
    Next
    INDEX
    Explanations

    data interchange format

    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
     doings
    -0.07
     can
    -0.06
    ではありません
    -0.06
     chock
    -0.06
     ஜோ
    -0.06
     one
    -0.06
     निराशा
    -0.06
    始める
    -0.06
     പ്രവര്‍ത്തന
    -0.06
    คู่
    -0.06
    POSITIVE LOGITS
    றவு
    0.06
     decir
    0.06
     зачем
    0.06
    Durante
    0.06
     falar
    0.06
     naturali
    0.06
     चर्चित
    0.06
     його
    0.06
     sogenannten
    0.06
    %,
    0.06
    Activations Density 0.001%

    No Known Activations