© 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. 116712
    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
    あらゆる
    -0.07
    après
    -0.07
     proverbial
    -0.06
     všechny
    -0.06
     vermiş
    -0.06
     Familie
    -0.06
     west
    -0.06
     unsuspecting
    -0.06
    すべての
    -0.06
     అన్ని
    -0.06
    POSITIVE LOGITS
     utilizzati
    0.06
    ذور
    0.06
     uso
    0.06
    ন্টি
    0.06
     assist
    0.06
    მართ
    0.06
     that
    0.06
     використа
    0.06
     wykorzyst
    0.05
     پاکستان
    0.05
    Activations Density 0.000%

    No Known Activations