© 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. 117483
    Prev
    Next
    INDEX
    Explanations

    web scraping and parsing beautifulsoup

    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
    ↵↵↵↵↵
    -0.06
     सुरुवात
    -0.06
    开始
    -0.06
     strangely
    -0.06
     beginning
    -0.06
    就没有
    -0.06
     occasionally
    -0.06
     usually
    -0.05
     radiometric
    -0.05
    我
    -0.05
    POSITIVE LOGITS
     вновь
    0.07
     nuevos
    0.07
    верка
    0.07
     bár
    0.06
    áli
    0.06
    avana
    0.06
    זה
    0.06
    汎
    0.06
     했던
    0.06
     можете
    0.06
    Activations Density 0.026%

    No Known Activations