© 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. 130511
    Prev
    Next
    INDEX
    Explanations

    datasets, research, staff

    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
     sớm
    -0.07
     because
    -0.07
    保证
    -0.06
     başarılı
    -0.06
     นี้
    -0.06
     automatically
    -0.06
    菁
    -0.06
     automatisch
    -0.06
     timely
    -0.06
     perquè
    -0.06
    POSITIVE LOGITS
    माला
    0.06
     generali
    0.06
     cualquiera
    0.06
     thrilling
    0.06
    ukas
    0.06
     livid
    0.06
     cuyo
    0.05
     ماهی
    0.05
     cauldron
    0.05
    णे
    0.05
    Activations Density 0.003%

    No Known Activations