© 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. 130996
    Prev
    Next
    INDEX
    Explanations

    foreign accents or scripts

    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
     credence
    -0.06
    ця
    -0.05
     Rev
    -0.05
     बधाई
    -0.05
     اون
    -0.05
     любую
    -0.05
     almost
    -0.05
     মনে
    -0.05
    都要
    -0.05
    étude
    -0.05
    POSITIVE LOGITS
     sepak
    0.06
     vaste
    0.06
    比如
    0.06
     زندگی
    0.06
    Ciao
    0.06
     个
    0.06
     осень
    0.06
    悵
    0.06
     stelle
    0.06
    গ্রস্ত
    0.06
    Activations Density 0.022%

    No Known Activations