© 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. 118487
    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
     “
    -0.06
    齿
    -0.06
     FRI
    -0.06
     ‘‘
    -0.06
    នឹង
    -0.05
     in
    -0.05
    岡山
    -0.05
    黏
    -0.05
     في
    -0.05
     Super
    -0.05
    POSITIVE LOGITS
     Explanation
    0.07
    Explanation
    0.06
     몇
    0.06
     tujuh
    0.06
     explains
    0.06
    rograman
    0.06
     বাপ
    0.06
    imarães
    0.06
    BASELINE
    0.06
    快適
    0.06
    Activations Density 0.000%

    No Known Activations