© 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. 117126
    Prev
    Next
    INDEX
    Explanations

    Published, If, Privacy, Names

    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
    课堂
    -0.06
     класси
    -0.06
    Trail
    -0.06
    ريقه
    -0.06
    liberal
    -0.06
     класи
    -0.06
     liberals
    -0.06
    During
    -0.06
    elcome
    -0.06
    offensive
    -0.05
    POSITIVE LOGITS
     spreadsheet
    0.06
     Rico
    0.06
    ไม่มี
    0.06
    Integer
    0.06
     مرة
    0.06
     especializado
    0.06
     لدى
    0.06
     lettuce
    0.06
     close
    0.05
     immersed
    0.05
    Activations Density 0.001%

    No Known Activations