© 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. 128693
    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
    최
    -0.06
    재
    -0.06
     divs
    -0.06
     дизайн
    -0.06
    駐車場
    -0.06
     chatter
    -0.06
     หรือ
    -0.06
     gesetz
    -0.06
    青森
    -0.06
     повто
    -0.06
    POSITIVE LOGITS
     exhilarating
    0.06
     സഞ്ച
    0.06
    াত্র
    0.06
    using
    0.06
     প্রেম
    0.06
     tourists
    0.06
     rigorously
    0.05
    álně
    0.05
     Fourier
    0.05
     Palmer
    0.05
    Activations Density 0.000%

    No Known Activations