© 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. 128282
    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
     in
    -0.06
     Inhibition
    -0.06
     insight
    -0.06
    ә
    -0.06
     within
    -0.06
    中に
    -0.06
     amongst
    -0.06
    閾
    -0.06
     accompanied
    -0.06
    自动
    -0.06
    POSITIVE LOGITS
    drž
    0.06
    utama
    0.06
     specific
    0.06
    为什么
    0.06
    specific
    0.06
     dedicated
    0.06
    supports
    0.06
    Specific
    0.06
     основном
    0.06
    為什麼
    0.06
    Activations Density 0.000%

    No Known Activations