© 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. 130926
    Prev
    Next
    INDEX
    Explanations

    various formatting and declarations

    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
     gonna
    -0.07
     आणि
    -0.06
     nggak
    -0.06
     ও
    -0.06
    嚎
    -0.06
     ਅਤੇ
    -0.06
     নেয়ার
    -0.06
    tx
    -0.06
     dauer
    -0.06
    otov
    -0.06
    POSITIVE LOGITS
    :
    0.07
     কয়েকজন
    0.06
    BEGIN
    0.06
    Various
    0.06
     Various
    0.06
     countless
    0.05
     поступи
    0.05
     glance
    0.05
    begin
    0.05
     PERCENT
    0.05
    Activations Density 0.004%

    No Known Activations