© 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. 115918
    Prev
    Next
    INDEX
    Explanations

    help me

    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
     použív
    -0.07
     verwendet
    -0.06
     use
    -0.06
     verwenden
    -0.06
     usare
    -0.06
     استفاده
    -0.06
     uses
    -0.06
    èvre
    -0.06
     youre
    -0.06
     사용
    -0.06
    POSITIVE LOGITS
    ama
    0.06
    翻译
    0.06
     karena
    0.06
     each
    0.06
     Mỗi
    0.06
     cuma
    0.06
     অনেকে
    0.06
     తమ
    0.06
    some
    0.06
     någon
    0.06
    Activations Density 0.022%

    No Known Activations