© 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. 128145
    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
     TN
    -0.06
     homolog
    -0.06
     როგორც
    -0.06
    atres
    -0.06
     theo
    -0.06
     طالب
    -0.06
     उपसर्ग
    -0.06
    เหมือน
    -0.06
     như
    -0.06
     as
    -0.06
    POSITIVE LOGITS
     greetings
    0.06
     That
    0.06
     Yup
    0.06
     धा
    0.06
      
    0.06
    Baik
    0.06
    냐
    0.06
    Ine
    0.06
     დაბ
    0.06
     gând
    0.06
    Activations Density 0.000%

    No Known Activations