© 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. 120117
    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
     newly
    -0.07
     melhorar
    -0.06
     പുതു
    -0.06
     allow
    -0.06
     allows
    -0.06
    ここでは
    -0.06
     gled
    -0.06
     antérieure
    -0.06
     புது
    -0.06
     অনেক
    -0.06
    POSITIVE LOGITS
     hiyo
    0.08
     этому
    0.06
     diesem
    0.06
    はその
    0.06
     sowie
    0.06
     всю
    0.06
     такую
    0.06
     হস্তে
    0.06
    assertRaises
    0.06
    िसू
    0.06
    Activations Density 0.000%

    No Known Activations