© 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. 117532
    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
     करताना
    -0.06
    erne
    -0.06
    ؛
    -0.06
     prematurely
    -0.06
     今天
    -0.05
     মিটিং
    -0.05
    なども
    -0.05
    泸
    -0.05
    preference
    -0.05
    जन
    -0.05
    POSITIVE LOGITS
     it
    0.07
     for
    0.07
     теорети
    0.06
     thoughtful
    0.06
     assorted
    0.06
     be
    0.06
     to
    0.06
    oretically
    0.06
     тебе
    0.06
     করিতে
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.