© 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. 130150
    Prev
    Next
    INDEX
    Explanations

    `<!DOCTYPE` or `<html>` tags

    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
    当初
    -0.06
     její
    -0.06
    们
    -0.06
     तैर
    -0.06
    其
    -0.06
     saw
    -0.05
     पड़ी
    -0.05
     הראש
    -0.05
     verlo
    -0.05
     đỉnh
    -0.05
    POSITIVE LOGITS
     Yup
    0.07
    தாவது
    0.07
     bazı
    0.06
     egy
    0.06
     aunque
    0.06
     সন্ত্রাস
    0.06
    enaar
    0.06
     Yeah
    0.06
     Bandung
    0.06
     affordable
    0.06
    Activations Density 0.001%

    No Known Activations