© 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. 129861
    Prev
    Next
    INDEX
    Explanations

    how can I

    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
     resposta
    -0.07
     debido
    -0.07
     compd
    -0.07
    ०
    -0.07
     quinto
    -0.06
     верх
    -0.06
     közö
    -0.06
     ehemalige
    -0.06
     communauté
    -0.06
     aceste
    -0.06
    POSITIVE LOGITS
     now
    0.07
    now
    0.06
    <i>
    0.06
     všechny
    0.06
     все
    0.06
     늘
    0.06
     всі
    0.06
    现在
    0.06
    ,
    0.06
    ‌ನ
    0.06
    Activations Density 0.115%

    No Known Activations