© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 129553
    Prev
    Next
    INDEX
    Explanations

    financial and legal advice

    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
     الأطفال
    -0.06
     tige
    -0.06
    нях
    -0.06
     nourrice
    -0.06
     качества
    -0.06
     требования
    -0.06
     જન્મ
    -0.06
     بچوں
    -0.06
    umbnail
    -0.06
     खासियत
    -0.05
    POSITIVE LOGITS
     βοη
    0.08
    方法
    0.07
    方法的
    0.07
    relief
    0.06
     মোকাবেলা
    0.06
     izol
    0.06
    解决方案
    0.06
     advisers
    0.06
    カウン
    0.06
     asta
    0.06
    Activations Density 0.002%

    No Known Activations