© 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. 119995
    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
    Prayer
    -0.07
     Ausland
    -0.06
    prayer
    -0.06
     മറ്റൊരു
    -0.06
    rijven
    -0.06
     purifying
    -0.06
    រប
    -0.06
    凭借
    -0.06
     Prayer
    -0.06
     दलित
    -0.06
    POSITIVE LOGITS
    debug
    0.06
     М
    0.06
     ג
    0.06
    खोरी
    0.06
    হিন্দু
    0.05
    そうです
    0.05
    imbang
    0.05
    㭂
    0.05
     insiders
    0.05
     Возможно
    0.05
    Activations Density 0.000%

    No Known Activations