© 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. 120561
    Prev
    Next
    INDEX
    Explanations

    quoted speech followed by "I", "It", "My"

    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
    全部
    -0.08
     zcela
    -0.07
    全く
    -0.07
     teljesen
    -0.07
    是可以
    -0.06
     tamamen
    -0.06
     całkow
    -0.06
     völl
    -0.06
     완전히
    -0.06
    有可能
    -0.06
    POSITIVE LOGITS
     four
    0.06
    pexels
    0.06
     seven
    0.06
     According
    0.06
     three
    0.06
     It
    0.06
     For
    0.06
     their
    0.06
     eight
    0.06
     five
    0.06
    Activations Density 0.006%

    No Known Activations