© 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. 129830
    Prev
    Next
    INDEX
    Explanations

    Christmas tree

    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
     शीतल
    -0.06
     Quatre
    -0.06
     recalcul
    -0.06
     tries
    -0.06
     wealthiest
    -0.06
     произо
    -0.06
     Jum
    -0.05
     দিগ
    -0.05
     karena
    -0.05
     отриму
    -0.05
    POSITIVE LOGITS
     without
    0.07
     dáng
    0.06
     молодо
    0.06
    without
    0.06
     Ahmet
    0.06
     ভক্ত
    0.06
    доступ
    0.06
     चुनौ
    0.06
    datasets
    0.06
     attracting
    0.06
    Activations Density 0.019%

    No Known Activations