© 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. 118351
    Prev
    Next
    INDEX
    Explanations

    code-related punctuation and mixed languages

    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
     kuitenkin
    -0.07
     primero
    -0.07
     everybody
    -0.06
     没有
    -0.06
     żeby
    -0.06
    Everybody
    -0.06
    ござい
    -0.06
     hasn
    -0.06
     sufficiently
    -0.06
     to
    -0.06
    POSITIVE LOGITS
    );
    0.06
     célé
    0.06
     overall
    0.06
    ור
    0.06
     ২০১৯
    0.06
     jeweil
    0.05
    হতের
    0.05
    হত্যার
    0.05
    ＊＊
    0.05
    도로
    0.05
    Activations Density 0.001%

    No Known Activations