© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 119052
    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
     tylko
    -0.07
    only
    -0.07
     only
    -0.07
    ONLY
    -0.07
    Only
    -0.07
     developers
    -0.06
     csak
    -0.06
     hoş
    -0.06
     perchè
    -0.06
    当天
    -0.06
    POSITIVE LOGITS
    でしょうか
    0.07
    ？
    0.07
     year
    0.07
     did
    0.07
    になった
    0.07
     آیا
    0.07
    Year
    0.06
     tahun
    0.06
     사용하여
    0.06
    ですか
    0.06
    Activations Density 0.000%

    No Known Activations