© 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. 131059
    Prev
    Next
    INDEX
    Explanations

    class names after import

    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
     disclosing
    -0.06
    各种
    -0.06
     something
    -0.06
     পুর্ব
    -0.06
     expressing
    -0.06
    十年
    -0.06
    árt
    -0.06
     چیز
    -0.05
     مواد
    -0.05
     associating
    -0.05
    POSITIVE LOGITS
     оптима
    0.07
     všechny
    0.06
    দ্বিত
    0.06
     аналоги
    0.06
     souhaite
    0.06
     Где
    0.06
    ब्ब
    0.06
    応用
    0.06
     stesso
    0.06
    Jogador
    0.06
    Activations Density 0.002%

    No Known Activations