© 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. 115941
    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
     स्क्
    -0.06
    ጨም
    -0.06
     enormously
    -0.06
     চিৎ
    -0.06
     যৌ
    -0.05
     tremendously
    -0.05
     consistently
    -0.05
    longrightarrow
    -0.05
     rationality
    -0.05
     functions
    -0.05
    POSITIVE LOGITS
     ఇక
    0.08
    なら
    0.07
     rồi
    0.07
     ਲਈ
    0.07
    তবে
    0.07
     প্রতিদিন
    0.06
    趣味
    0.06
     heaps
    0.06
     ან
    0.06
    ắp
    0.06
    Activations Density 0.000%

    No Known Activations