© 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. 130696
    Prev
    Next
    INDEX
    Explanations

    programming and code snippets

    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
     दूसरी
    -0.06
    ;
    -0.06
     
    -0.06
    quickly
    -0.06
    by
    -0.06
     quickly
    -0.06
     vite
    -0.06
     brut
    -0.05
    ge
    -0.05
    ኋላ
    -0.05
    POSITIVE LOGITS
    を除
    0.07
    mysql
    0.06
     duas
    0.06
     plán
    0.06
     پنج
    0.06
     రెండు
    0.06
     budú
    0.06
    都知道
    0.06
     Adam
    0.06
     định
    0.06
    Activations Density 0.001%

    No Known Activations