© 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. 130486
    Prev
    Next
    INDEX
    Explanations

    Plaintiff, Defendant, Appellant

    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
    ானது
    -0.07
     ஆனது
    -0.06
     ayrıca
    -0.06
     creo
    -0.06
     продолжаем
    -0.06
     continues
    -0.06
     संबंधित
    -0.06
    ឬ
    -0.06
     επίσης
    -0.06
    slategray
    -0.06
    POSITIVE LOGITS
     পরিত্র
    0.07
     first
    0.06
    第一個
    0.06
    first
    0.05
     First
    0.05
     This
    0.05
    ปาก
    0.05
     मिल
    0.05
    第一
    0.05
     dearest
    0.05
    Activations Density 0.002%

    No Known Activations