© 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. 118780
    Prev
    Next
    INDEX
    Explanations

    brain parts and medical terms

    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
     ইন্
    -0.06
     již
    -0.06
     sailing
    -0.06
     বিচ
    -0.05
     centered
    -0.05
     groupe
    -0.05
     group
    -0.05
     fancied
    -0.05
    ಮೀ
    -0.05
    closure
    -0.05
    POSITIVE LOGITS
    SessionFactory
    0.07
     ellos
    0.06
     Taco
    0.06
     завод
    0.06
     haber
    0.06
     얘기를
    0.06
     momento
    0.06
     বিষয়ে
    0.06
     they
    0.06
     자료
    0.06
    Activations Density 0.042%

    No Known Activations