© 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. 130749
    Prev
    Next
    INDEX
    Explanations

    foreign or unicode characters

    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
     to
    -0.06
     כדי
    -0.06
     tìm
    -0.05
     ekstrem
    -0.05
     rugged
    -0.05
     ኩ
    -0.05
     म्हणजे
    -0.05
     To
    -0.05
    我去
    -0.05
     archaeologist
    -0.05
    POSITIVE LOGITS
     বিদেশী
    0.07
     embassy
    0.07
    出口
    0.07
    ＋
    0.06
     Embassy
    0.06
     北京
    0.06
     स्वागत
    0.06
     dubbed
    0.06
    チケット
    0.06
    foreign
    0.06
    Activations Density 0.004%

    No Known Activations