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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 120619
    Prev
    Next
    INDEX
    Explanations

    References: [@B1]

    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
    いで
    -0.06
     hampir
    -0.06
     что
    -0.06
     नया
    -0.06
     Educators
    -0.06
     waxay
    -0.06
    では
    -0.06
     ещё
    -0.06
     ಎಲ್ಲಾ
    -0.06
     sẽ
    -0.06
    POSITIVE LOGITS
    ্যারি
    0.06
    のひとつ
    0.06
    我知道
    0.06
     always
    0.06
     همیشه
    0.06
    ulae
    0.06
     боюнча
    0.06
     none
    0.06
    条件的
    0.06
     classically
    0.06
    Activations Density 0.012%

    No Known Activations