© 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. 130075
    Prev
    Next
    INDEX
    Explanations

    measurement units and numbers

    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
     dance
    -0.07
     అంబేద్కర్
    -0.06
     Bén
    -0.06
     Dance
    -0.06
     Fremont
    -0.06
     نمبر
    -0.06
     моей
    -0.06
     你
    -0.06
     droid
    -0.06
    Dance
    -0.06
    POSITIVE LOGITS
     with
    0.06
     بى
    0.06
     sva
    0.06
     allah
    0.06
    ជាមួយ
    0.06
     independ
    0.06
    さまざまな
    0.06
     दिखाना
    0.06
     nesses
    0.06
    在新
    0.06
    Activations Density 0.004%

    No Known Activations