© 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. 116447
    Prev
    Next
    INDEX
    Explanations

    Jay Z, Mai-Mai, Hand grip, Q: , Recent News

    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
     tous
    -0.06
     especializados
    -0.06
     비해
    -0.06
     especializado
    -0.05
    真实的
    -0.05
     Dant
    -0.05
    Descripcion
    -0.05
    那
    -0.05
     বাজার
    -0.05
     उच्चारण
    -0.05
    POSITIVE LOGITS
     gyak
    0.06
    льзя
    0.06
     elección
    0.06
     phasing
    0.06
    เลือก
    0.06
     lựa
    0.06
    楝
    0.06
     นอน
    0.06
    There
    0.06
     úspě
    0.06
    Activations Density 0.001%

    No Known Activations