© 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. 118431
    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
                             
    -0.07
                           
    -0.06
              
    -0.06
               
    -0.06
                     
    -0.06
     快
    -0.06
    several
    -0.06
     several
    -0.06
     多い
    -0.06
                      
    -0.06
    POSITIVE LOGITS
     neue
    0.07
     eggplant
    0.07
    Ꮭ
    0.07
     nuove
    0.06
     recentemente
    0.06
     nuovo
    0.06
     andere
    0.06
     nieuwe
    0.06
     other
    0.06
     새로운
    0.06
    Activations Density 0.000%

    No Known Activations