© 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. 128170
    Prev
    Next
    INDEX
    Explanations

    drug names

    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
     dís
    -0.06
     retir
    -0.06
     ويل
    -0.06
    )-(
    -0.06
     свадь
    -0.06
     именно
    -0.06
    複数
    -0.06
    多
    -0.06
     inilah
    -0.06
    ]-[
    -0.05
    POSITIVE LOGITS
     impresses
    0.07
     bekannten
    0.07
     célèbre
    0.07
     Substitute
    0.06
     μας
    0.06
    傳統
    0.06
     traditionnelle
    0.06
     due
    0.06
     тради
    0.06
    Reach
    0.06
    Activations Density 0.026%

    No Known Activations