© 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. 128428
    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
    的就是
    -0.06
    的是
    -0.06
     sporo
    -0.06
     konkret
    -0.05
    Wales
    -0.05
    ４
    -0.05
     שה
    -0.05
    땐
    -0.05
     yksi
    -0.05
    When
    -0.05
    POSITIVE LOGITS
     ไม่
    0.07
     không
    0.07
     ไม่มี
    0.06
     இதனால்
    0.06
     Myself
    0.06
     не
    0.06
    ไม่
    0.06
    🤗
    0.06
    没有
    0.06
    または
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.