© 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. 120351
    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
     condições
    -0.06
     И
    -0.06
     조건
    -0.06
     условии
    -0.06
    ActionResult
    -0.06
     the
    -0.06
     our
    -0.06
     І
    -0.06
     مخت
    -0.06
     ishlab
    -0.06
    POSITIVE LOGITS
    también
    0.07
     प्रकरण
    0.06
     '/',
    0.06
     بسیاری
    0.06
     এটাও
    0.06
     części
    0.06
     প্রথমেই
    0.06
     설명을
    0.06
     before
    0.06
    ION
    0.06
    Activations Density 0.000%

    No Known Activations