© 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. 130714
    Prev
    Next
    INDEX
    Explanations

    no other ... more

    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
     niet
    -0.08
     nicht
    -0.07
    되지
    -0.07
    ไม่ได้
    -0.07
     không
    -0.07
     leuke
    -0.07
     não
    -0.06
     रेत
    -0.06
     của
    -0.06
     ikke
    -0.06
    POSITIVE LOGITS
     consistently
    0.07
    这
    0.07
    これ
    0.06
     this
    0.06
    這
    0.06
     which
    0.06
    )、
    0.06
     that
    0.06
     or
    0.06
     вот
    0.06
    Activations Density 0.019%

    No Known Activations