© 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. 120417
    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
    などで
    -0.08
    ต่างๆ
    -0.08
    などが
    -0.07
     등으로
    -0.07
    などの
    -0.07
     ligado
    -0.07
     등의
    -0.06
    など
    -0.06
     المختلف
    -0.06
    などは
    -0.06
    POSITIVE LOGITS
     tersedia
    0.06
     disponibles
    0.06
     PURCHASE
    0.06
    专用
    0.06
     disponible
    0.06
     هناك
    0.06
     specially
    0.06
     我们
    0.06
     Disponible
    0.06
    Disponible
    0.06
    Activations Density 0.000%

    No Known Activations