© 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. 130814
    Prev
    Next
    INDEX
    Explanations

    invention

    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
     finalement
    -0.06
     आखिरकार
    -0.06
    ẳ
    -0.06
     finalmente
    -0.06
    ospitals
    -0.06
     desired
    -0.06
    ं
    -0.06
    ल्
    -0.06
     desires
    -0.06
    IBM
    -0.06
    POSITIVE LOGITS
     संदेश
    0.07
     മറ്റു
    0.07
     Brief
    0.07
     Inform
    0.06
    Brief
    0.06
    ান্ত্রিক
    0.06
     illetve
    0.06
     ayl
    0.06
     ശിഷ്യ
    0.06
     text
    0.06
    Activations Density 0.007%

    No Known Activations