© 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. 121003
    Prev
    Next
    INDEX
    Explanations

    of a

    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
     the
    -0.07
     that
    -0.07
     their
    -0.06
     durant
    -0.06
     a
    -0.06
     THAT
    -0.06
     loosing
    -0.06
     publicity
    -0.06
     haberse
    -0.06
     its
    -0.06
    POSITIVE LOGITS
     aceste
    0.07
     can
    0.06
    သွား
    0.06
     kedua
    0.06
    と思います
    0.06
    两个人
    0.06
    ↵
    0.06
     পর্যন্ত
    0.06
     নির্দিষ্ট
    0.06
     સારી
    0.06
    Activations Density 0.012%

    No Known Activations