© 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. 117113
    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
     or
    -0.07
     Meso
    -0.07
     henüz
    -0.07
    差不多
    -0.07
     هنوز
    -0.06
     Other
    -0.06
                           
    -0.06
    尚未
    -0.06
     Whereas
    -0.06
                               
    -0.06
    POSITIVE LOGITS
     your
    0.06
     this
    0.06
     potrivit
    0.06
     niekoľ
    0.06
     বিভিন্ন
    0.06
    三
    0.06
     několik
    0.06
     खी
    0.05
     কয়েকটি
    0.05
     তিনটি
    0.05
    Activations Density 0.000%

    No Known Activations