© 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. 128083
    Prev
    Next
    INDEX
    Explanations

    cyclin proteins

    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
    ilihan
    -0.06
    option
    -0.06
    ليز
    -0.06
    waiting
    -0.06
    インタ
    -0.06
    ->
    -0.06
     ->
    -0.06
     Rosie
    -0.06
    oloj
    -0.06
     مقابلے
    -0.06
    POSITIVE LOGITS
     처음
    0.07
     यात्री
    0.06
     first
    0.06
     primeros
    0.06
     первое
    0.06
    czeniu
    0.06
     primeiro
    0.06
     専用
    0.06
    使う
    0.06
     Laus
    0.06
    Activations Density 0.002%

    No Known Activations