© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118102
    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
     skute
    -0.06
     ন্যায
    -0.06
    +...+
    -0.06
     اجتماع
    -0.06
     змо
    -0.06
     Power
    -0.06
     टूटा
    -0.06
    jaty
    -0.05
     طل
    -0.05
     действительно
    -0.05
    POSITIVE LOGITS
     मुद्दे
    0.07
     slightly
    0.06
     aesthetically
    0.06
    MDg
    0.06
    치를
    0.06
     Woodlands
    0.06
    duplicated
    0.06
    northern
    0.06
     făcut
    0.06
     northern
    0.06
    Activations Density 0.000%

    No Known Activations