© 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. 129250
    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
    iaz
    -0.05
    ধানে
    -0.05
     혹은
    -0.05
    ד
    -0.05
     the
    -0.05
    <footer>
    -0.05
     it
    -0.05
     Ub
    -0.05
     application
    -0.05
    もしくは
    -0.05
    POSITIVE LOGITS
     BUT
    0.06
     строительство
    0.06
     dvě
    0.06
    เหล่านี้
    0.06
     доступ
    0.06
     friday
    0.06
     தொலைக்காட்சி
    0.06
     অপেক্ষ
    0.06
     উপদেষ্টা
    0.06
     but
    0.06
    Activations Density 0.000%

    No Known Activations