© 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. 127929
    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
    বিচার
    -0.06
     सर्वप्रथम
    -0.06
     expected
    -0.06
     just
    -0.06
    ক্য
    -0.06
     खेती
    -0.06
     immediately
    -0.05
     preceded
    -0.05
    ಲೇ
    -0.05
     prieš
    -0.05
    POSITIVE LOGITS
    私は
    0.07
     outlines
    0.07
     unused
    0.07
     totiž
    0.06
     ваша
    0.06
    Phương
    0.06
     mạch
    0.06
    ㄹ
    0.06
     scaffolding
    0.06
     будут
    0.06
    Activations Density 0.000%

    No Known Activations