© 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. 120948
    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
     relatively
    -0.06
     পশ্চ
    -0.06
     مختلف
    -0.06
    第六
    -0.06
    第四
    -0.05
     predominantly
    -0.05
    ze
    -0.05
    第二
    -0.05
     पुनः
    -0.05
     версии
    -0.05
    POSITIVE LOGITS
     нес
    0.07
     giust
    0.07
     ದು
    0.07
     privado
    0.06
    ഷ്ട്ര
    0.06
     مقارنه
    0.06
     to
    0.06
     onları
    0.06
     диф
    0.06
     Guant
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.