© 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. 119305
    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
     особенно
    -0.07
     especially
    -0.07
     특히
    -0.07
     its
    -0.06
     ailes
    -0.06
     especialmente
    -0.06
     එහි
    -0.06
     குறிப்பாக
    -0.06
    天气
    -0.06
    那样
    -0.06
    POSITIVE LOGITS
     Deux
    0.07
     část
    0.07
    某个
    0.06
     ఎవ
    0.06
     particip
    0.06
     był
    0.06
    䢙
    0.06
    跟着
    0.06
    參與
    0.06
    üren
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.