© 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. 116185
    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
    他の
    -0.06
     อื่น
    -0.06
    ज़र
    -0.06
    Fallback
    -0.06
     cove
    -0.06
    ছন
    -0.06
    hore
    -0.06
     다른
    -0.06
    state
    -0.06
    Grove
    -0.06
    POSITIVE LOGITS
     непосредственно
    0.06
     énorme
    0.06
     enorme
    0.06
     invigor
    0.06
     എടു
    0.06
    到现在
    0.06
    立刻
    0.06
     पाठक
    0.06
     conclusively
    0.05
     জনসাধারণ
    0.05
    Activations Density 0.000%

    No Known Activations