© 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. 130225
    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
     tentar
    -0.06
     रिवाज
    -0.05
    一共
    -0.05
     mayoría
    -0.05
    开头
    -0.05
     busiest
    -0.05
    hope
    -0.05
     aiming
    -0.05
    那边
    -0.05
    vital
    -0.05
    POSITIVE LOGITS
    現在の
    0.06
     wirken
    0.06
             
    0.06
    接下來
    0.06
     irrespective
    0.06
    regardless
    0.06
     Москвы
    0.06
              
    0.06
    ুরা
    0.06
     incorporate
    0.06
    Activations Density 0.000%

    No Known Activations