© 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. 115887
    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
     рас
    -0.07
     hakkında
    -0.06
     мы
    -0.06
     솔
    -0.06
    には
    -0.06
    }--\
    -0.06
    করে
    -0.06
     турында
    -0.06
     შესახებ
    -0.06
     해
    -0.06
    POSITIVE LOGITS
     during
    0.06
    মণ্ড
    0.06
    少量
    0.06
    ယ်
    0.05
     মুক্তিযোদ্ধাদের
    0.05
    可惜
    0.05
     Penis
    0.05
     armored
    0.05
    Насе
    0.05
     concursos
    0.05
    Activations Density 0.000%

    No Known Activations