© 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. 120826
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     whims
    -0.07
     selectivity
    -0.07
    قط
    -0.06
     বিভক্ত
    -0.06
     cible
    -0.06
    魑
    -0.06
     fragmented
    -0.06
     villain
    -0.06
    複雑
    -0.06
     जटिल
    -0.06
    POSITIVE LOGITS
     автоматически
    0.07
     automaticamente
    0.06
    स्वास्थ्य
    0.06
     favour
    0.06
     bounding
    0.06
    会自动
    0.06
    Recogn
    0.06
    automatically
    0.06
     automatically
    0.06
     स्वास्थ्य
    0.06
    Activations Density 0.000%

    No Known Activations