© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 116582
    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
    Not in Any Lists

    No Comments

    Negative Logits
     город
    -0.06
     message
    -0.06
     streetlight
    -0.06
    '><
    -0.06
    쵝
    -0.06
     preparados
    -0.06
    град
    -0.06
     অপেক্ষা
    -0.06
     увиде
    -0.06
     anbef
    -0.06
    POSITIVE LOGITS
     транспорти
    0.07
     intrans
    0.07
     transporting
    0.07
     eql
    0.06
     transportation
    0.06
     []
    0.06
     transport
    0.06
     schönsten
    0.06
     accessing
    0.06
     به‌عنوان
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.