© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130739
    Prev
    Next
    INDEX
    Explanations

    Causes and treatments

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     superbe
    -0.07
     نموذج
    -0.07
     lifetimes
    -0.07
     aspects
    -0.07
    Businessman
    -0.06
     journey
    -0.06
     veik
    -0.06
    睿
    -0.06
     evaluation
    -0.06
     dimensions
    -0.06
    POSITIVE LOGITS
     enforce
    0.06
    手中的
    0.06
     prevailed
    0.06
     соблю
    0.06
     maintenir
    0.06
    手中
    0.06
    Equations
    0.06
     to
    0.06
    ,
    0.05
     enforcing
    0.05
    Activations Density 0.006%

    No Known Activations