© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 131027
    Prev
    Next
    INDEX
    Explanations

    court names and years

    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
    сюда
    -0.06
    ღ
    -0.06
     জারি
    -0.06
    never
    -0.05
    ())->
    -0.05
     daughters
    -0.05
     비롯
    -0.05
     never
    -0.05
     சாய
    -0.05
    Never
    -0.05
    POSITIVE LOGITS
    ଵ
    0.06
     what
    0.06
    チャン
    0.06
     transpar
    0.06
    意外
    0.06
     openai
    0.06
     MNIST
    0.06
     exce
    0.06
     standoff
    0.06
    thiop
    0.06
    Activations Density 0.001%

    No Known Activations