© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 116557
    Prev
    Next
    INDEX
    Explanations

    legal or formal document phrases

    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
     făcut
    -0.06
     начала
    -0.06
     doesn
    -0.06
     тео
    -0.06
    做什么
    -0.06
     nicht
    -0.06
     erster
    -0.06
     початку
    -0.06
     acoustic
    -0.06
     उपयोगकर्ताओं
    -0.06
    POSITIVE LOGITS
     الدوري
    0.06
    が出る
    0.06
     in
    0.06
     Ори
    0.06
     مدیر
    0.06
     letzte
    0.06
    ตำแหน่ง
    0.06
     a
    0.06
     kvalit
    0.06
     인터넷
    0.06
    Activations Density 0.001%

    No Known Activations