© 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. 117468
    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
     после
    -0.07
    ৩০
    -0.07
    ীদের
    -0.06
     Examiner
    -0.06
    龶
    -0.06
    特別
    -0.06
     SPECIAL
    -0.06
     برای
    -0.06
     Specialized
    -0.06
     アンティーク
    -0.06
    POSITIVE LOGITS
     just
    0.07
     encont
    0.06
     newer
    0.06
    That
    0.06
     experimentation
    0.06
     that
    0.06
     abruptly
    0.06
     Literally
    0.06
     माध्यमा
    0.06
     města
    0.06
    Activations Density 0.000%

    No Known Activations