© 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. 120006
    Prev
    Next
    INDEX
    Explanations

    android.os.Bundle

    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
     veuillez
    -0.06
    生產
    -0.06
     Courses
    -0.06
     Production
    -0.06
     Atlanta
    -0.06
     incidencia
    -0.06
     ishlab
    -0.06
     imong
    -0.06
     chemicals
    -0.06
     chúng
    -0.06
    POSITIVE LOGITS
     really
    0.07
     truly
    0.07
    有一
    0.06
    =-
    0.06
     somewhat
    0.06
    really
    0.06
    claiming
    0.06
    将在
    0.06
     balans
    0.06
     lako
    0.06
    Activations Density 0.001%

    No Known Activations