© 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. 130138
    Prev
    Next
    INDEX
    Explanations

    in the art

    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
     market
    -0.08
    任何
    -0.07
     કોઈ
    -0.06
     sofort
    -0.06
     কেউ
    -0.06
     product
    -0.06
     process
    -0.06
     کوئی
    -0.06
     местных
    -0.06
     Nuclear
    -0.06
    POSITIVE LOGITS
     also
    0.06
    駕
    0.06
    들어
    0.06
     أيضا
    0.06
    трен
    0.06
     إلى
    0.06
    ilang
    0.06
     በት
    0.06
    আচ্ছা
    0.06
     aktual
    0.05
    Activations Density 0.003%

    No Known Activations