© 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. 127960
    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
     sonra
    -0.07
     their
    -0.06
     American
    -0.05
    atten
    -0.05
     then
    -0.05
     fles
    -0.05
    Market
    -0.05
     आदर्श
    -0.05
    ਫ
    -0.05
     stereotypes
    -0.05
    POSITIVE LOGITS
     অক্সিজ
    0.06
    緊急
    0.06
     Eugenio
    0.06
     Usually
    0.06
    आत्म
    0.06
     usually
    0.06
     обычно
    0.06
     essentially
    0.06
     Trauma
    0.06
     для
    0.06
    Activations Density 0.002%

    No Known Activations