© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 130898
    Prev
    Next
    INDEX
    Explanations

    answer/question separators

    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
     with
    -0.07
     επίσης
    -0.07
     점점
    -0.06
    也将
    -0.06
     माझ्या
    -0.06
     оптими
    -0.06
     меня
    -0.06
     رسمی
    -0.06
     Whats
    -0.06
     মুহাম্মদ
    -0.06
    POSITIVE LOGITS
     although
    0.07
    虽然
    0.06
     obwohl
    0.06
    Although
    0.06
    although
    0.06
    Answer
    0.06
    正好
    0.06
     answered
    0.06
     aunque
    0.06
    );
    0.06
    Activations Density 0.013%

    No Known Activations