© 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. 130830
    Prev
    Next
    INDEX
    Explanations

    gene polymorphism

    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
     detection
    -0.07
     detecting
    -0.07
    检测
    -0.06
     preexisting
    -0.06
    歴史
    -0.06
     monitoring
    -0.06
     functionalities
    -0.06
     Detecting
    -0.06
    样例
    -0.06
     lamps
    -0.05
    POSITIVE LOGITS
     kém
    0.06
     you
    0.06
     ఎక్కువ
    0.06
    mute
    0.06
     পরমাণ
    0.06
     oui
    0.06
     அவரது
    0.06
    清洁
    0.06
    ruik
    0.06
     இவரது
    0.06
    Activations Density 0.006%

    No Known Activations