© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 129820
    Prev
    Next
    INDEX
    Explanations

    percent decline or drop

    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
     of
    -0.09
     will
    -0.07
     when
    -0.07
     your
    -0.07
    اسی
    -0.06
     exp
    -0.06
     exponentially
    -0.06
     akan
    -0.06
     significantly
    -0.06
     oran
    -0.06
    POSITIVE LOGITS
     niž
    0.06
     które
    0.06
     (#{
    0.06
    还有一个
    0.06
     सब्ज
    0.06
     debajo
    0.06
     ጎ
    0.06
     fashionable
    0.06
     Consol
    0.06
    结局
    0.06
    Activations Density 0.010%

    No Known Activations