© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118139
    Prev
    Next
    INDEX
    Explanations

    UI element names and structure

    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
    خرى
    -0.08
     เป็น
    -0.07
     মুহুর্তে
    -0.07
     পরবর্তীতে
    -0.07
    打破
    -0.07
    ເປັນ
    -0.07
     প্রতিহিংস
    -0.07
    有望
    -0.07
     huit
    -0.07
     represents
    -0.06
    POSITIVE LOGITS
     \,
    0.06
    ↵↵
    0.05
    diary
    0.05
     hijos
    0.05
     incluso
    0.05
    ,
    0.05
    und
    0.05
     ciò
    0.05
     වල
    0.05
    any
    0.05
    Activations Density 0.006%

    No Known Activations