© 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. 130945
    Prev
    Next
    INDEX
    Explanations

    visual styles and text rendering

    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
     tiež
    -0.08
     probabilmente
    -0.07
    也将
    -0.07
     সম্ভবত
    -0.07
     também
    -0.07
    Probably
    -0.07
     provavelmente
    -0.06
    将于
    -0.06
     полови
    -0.06
     Xuân
    -0.06
    POSITIVE LOGITS
     condition
    0.06
    극
    0.06
     Charles
    0.05
     जोन
    0.05
    Os
    0.05
    にお
    0.05
     rightly
    0.05
     エ
    0.05
     भेट
    0.05
     дій
    0.05
    Activations Density 0.002%

    No Known Activations