© 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. 115869
    Prev
    Next
    INDEX
    Explanations

    gene regulation expression

    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
     изменение
    -0.08
     เขา
    -0.07
     insanların
    -0.07
    他在
    -0.07
     изменения
    -0.07
    Jakarta
    -0.06
    บคุม
    -0.06
    他对
    -0.06
    他是
    -0.06
     seinem
    -0.06
    POSITIVE LOGITS
     successively
    0.06
    建築
    0.06
     cette
    0.06
     Building
    0.06
     micro
    0.06
     building
    0.05
     ésta
    0.05
     rostro
    0.05
    建筑
    0.05
    让她
    0.05
    Activations Density 0.003%

    No Known Activations