© 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. 131035
    Prev
    Next
    INDEX
    Explanations

    academic titles

    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
     마무리
    -0.07
     två
    -0.07
     deux
    -0.07
     garnish
    -0.07
     cuatro
    -0.07
    ւ
    -0.06
     fyra
    -0.06
     zwei
    -0.06
     괜
    -0.06
     in
    -0.06
    POSITIVE LOGITS
     innovative
    0.07
     BOTH
    0.07
     नवीनतम
    0.07
     situations
    0.06
    不仅
    0.06
     selected
    0.06
     choices
    0.06
     activities
    0.06
     &
    0.06
     Innovative
    0.06
    Activations Density 0.002%

    No Known Activations