© 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. 120833
    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
     one
    -0.07
    Linea
    -0.06
     storia
    -0.06
     zs
    -0.06
    短い
    -0.06
     mniej
    -0.05
     arke
    -0.05
     linea
    -0.05
    න්ට
    -0.05
     achet
    -0.05
    POSITIVE LOGITS
    这
    0.07
    ここまで
    0.06
     ,
    0.06
     diesen
    0.06
     seules
    0.06
    此前
    0.06
     বিস্ম
    0.06
     dù
    0.06
     лишь
    0.06
     diese
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.