© 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. 130567
    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
    +,
    -0.07
    +][
    -0.06
     เหมือน
    -0.06
     ignored
    -0.06
    iqu
    -0.06
    <0xE1>
    -0.06
    +.
    -0.06
     সর্বত্র
    -0.06
    最後まで
    -0.06
    ̬
    -0.06
    POSITIVE LOGITS
    гран
    0.06
     بتح
    0.06
    ampuan
    0.06
     从
    0.06
     그
    0.06
     ग्रामीणों
    0.06
     από
    0.06
     પો
    0.06
     ম
    0.06
     từ
    0.06
    Activations Density 0.000%

    No Known Activations