© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118974
    Prev
    Next
    INDEX
    Explanations

    . / separator

    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
     ವಿವಿಧ
    -0.07
    bakan
    -0.07
     altında
    -0.06
     ಇದರಿಂದ
    -0.06
     অস্বাভাবিক
    -0.06
     পরিমাণে
    -0.06
     backgrounds
    -0.06
    줍니다
    -0.06
     some
    -0.06
     Various
    -0.06
    POSITIVE LOGITS
     рейтин
    0.07
    Ви
    0.06
    declared
    0.06
     FullHD
    0.06
    িত্র
    0.05
    ாக்
    0.05
    VIAF
    0.05
    Не
    0.05
    ГА
    0.05
    
    0.05
    Activations Density 0.015%

    No Known Activations