© 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. 120998
    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
    *:
    -0.07
     объектов
    -0.06
     ஸ்மார
    -0.06
     गिवन
    -0.06
    !:
    -0.06
     ਰਹ
    -0.06
     ':
    -0.06
     postseason
    -0.06
    ოვანი
    -0.06
     lumineux
    -0.06
    POSITIVE LOGITS
     we
    0.07
    现在
    0.06
     now
    0.06
     nous
    0.06
    現在
    0.06
     this
    0.06
    iamo
    0.06
     irmão
    0.06
     sním
    0.06
    น์
    0.06
    Activations Density 0.000%

    No Known Activations