© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 118903
    Prev
    Next
    INDEX
    Explanations

    legal citations and court opinions

    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
     efficacious
    -0.06
    コミュニケーション
    -0.06
     exhilarating
    -0.06
     new
    -0.06
     codef
    -0.06
     এবারের
    -0.05
    挨拶
    -0.05
     occupational
    -0.05
     jagged
    -0.05
     outstretched
    -0.05
    POSITIVE LOGITS
    дование
    0.07
     не
    0.07
     ਨਹੀਂ
    0.07
    டன
    0.07
     умови
    0.06
     সিরিজ
    0.06
     احتمال
    0.06
    irthday
    0.06
     không
    0.06
    真
    0.06
    Activations Density 0.002%

    No Known Activations