© 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. 115935
    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
     comprises
    -0.06
     эти
    -0.06
     لكرة
    -0.06
     이걸
    -0.06
     queste
    -0.06
     Amongst
    -0.06
     these
    -0.06
     αυτές
    -0.06
     chúng
    -0.06
     الحركة
    -0.06
    POSITIVE LOGITS
     which
    0.07
     নগদ
    0.06
    ósticos
    0.06
     simulators
    0.06
    ளாவ
    0.06
    ដែល
    0.06
     др
    0.06
    Synt
    0.06
    số
    0.06
     drastically
    0.06
    Activations Density 0.000%

    No Known Activations