© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130870
    Prev
    Next
    INDEX
    Explanations

    division and multiplication

    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
    Not in Any Lists

    No Comments

    Negative Logits
     debat
    -0.07
    または
    -0.07
     or
    -0.07
    ृत्य
    -0.07
     или
    -0.07
    或
    -0.06
     లేదా
    -0.06
     ಅಥವಾ
    -0.06
     അല്ലെങ്കിൽ
    -0.06
     یا
    -0.06
    POSITIVE LOGITS
     this
    0.07
     the
    0.07
    when
    0.06
    這個
    0.06
     various
    0.06
    imeric
    0.06
     like
    0.06
     what
    0.05
     этот
    0.05
     này
    0.05
    Activations Density 0.002%

    No Known Activations