© 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. 130459
    Prev
    Next
    INDEX
    Explanations

    programming identifiers and methods

    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
     broadcasts
    -0.06
    默认
    -0.06
    tight
    -0.06
     athletic
    -0.06
     continuously
    -0.06
     Winslow
    -0.06
     ह्यू
    -0.05
     facing
    -0.05
    允许
    -0.05
    低
    -0.05
    POSITIVE LOGITS
     était
    0.07
     ブリ
    0.06
    cat
    0.06
     berguna
    0.06
     underworld
    0.06
     ক্ষয়ক্ষ
    0.06
     これは
    0.06
     ফেলেছেন
    0.06
    net
    0.05
    était
    0.05
    Activations Density 0.002%

    No Known Activations