© 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. 120810
    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
    Not in Any Lists

    No Comments

    Negative Logits
     حوالے
    -0.06
    <0xEF>
    -0.06
    挪
    -0.06
    另外
    -0.06
     uwagę
    -0.06
    Ä
    -0.05
    pla
    -0.05
     brooding
    -0.05
     καθώς
    -0.05
     ハート
    -0.05
    POSITIVE LOGITS
     edo
    0.06
    私は
    0.06
     सफल
    0.06
     exemples
    0.06
     टूटा
    0.06
    Apache
    0.06
    Combining
    0.06
    缺失
    0.06
     আদাল
    0.06
     industrie
    0.06
    Activations Density 0.000%

    No Known Activations