© 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. 128032
    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
      
    -0.06
     Ра
    -0.06
    Profes
    -0.06
     aggregates
    -0.06
    Yet
    -0.05
     vì
    -0.05
    ന്തപു
    -0.05
     así
    -0.05
     così
    -0.05
     существу
    -0.05
    POSITIVE LOGITS
     долларов
    0.06
     risques
    0.06
    billed
    0.06
     tells
    0.06
    ñ
    0.06
    ごとに
    0.06
     transcends
    0.06
    厘米
    0.06
    トラブル
    0.06
     elke
    0.06
    Activations Density 0.000%

    No Known Activations