© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 115980
    Prev
    Next
    INDEX
    Explanations

    configuration, load, conversion, dataset, catwalk, Overstrand

    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
    Negative Logits
     klasse
    -0.07
     hadiah
    -0.06
     algunas
    -0.06
    搭载
    -0.06
    GULD
    -0.06
     sınıf
    -0.06
    单位
    -0.06
    nvidia
    -0.06
    测试
    -0.06
     Klasse
    -0.06
    POSITIVE LOGITS
     conveniently
    0.07
     rende
    0.06
     paediatric
    0.06
     comprise
    0.06
     overlooked
    0.06
     ইতোমধ্যে
    0.06
     comprises
    0.06
     extensive
    0.06
     COMPONENTS
    0.06
    ປະກອບ
    0.06
    Activations Density 0.001%

    No Known Activations