© 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. 115927
    Prev
    Next
    INDEX
    Explanations

    database search terms

    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
    👍
    -0.07
     Cannot
    -0.06
     并
    -0.06
    И
    -0.06
    electron
    -0.06
     reunión
    -0.06
     Tse
    -0.06
    加强
    -0.05
     electron
    -0.05
     pago
    -0.05
    POSITIVE LOGITS
     '.')
    0.07
    買い物
    0.06
    ่ม
    0.06
     الجديدة
    0.06
     proceeds
    0.06
    keletal
    0.06
    আমাদের
    0.06
     основу
    0.06
     структур
    0.06
     Sotheby
    0.06
    Activations Density 0.002%

    No Known Activations