© 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. 118900
    Prev
    Next
    INDEX
    Explanations

    medical imaging and data acquisition

    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
     facilitates
    -0.07
    ــ
    -0.07
     inextricably
    -0.07
    FDMA
    -0.06
     автомобиль
    -0.06
     эффектив
    -0.06
     provides
    -0.06
     impede
    -0.06
    两者
    -0.06
     prevents
    -0.06
    POSITIVE LOGITS
    data
    0.07
    组成的
    0.06
     only
    0.06
     тільки
    0.06
     gotten
    0.06
     только
    0.06
     your
    0.06
     you
    0.06
     Congratulations
    0.06
    只想
    0.06
    Activations Density 0.028%

    No Known Activations