© 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. 118219
    Prev
    Next
    INDEX
    Explanations

    lists and connecting phrase

    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
     వ్యక్తి
    -0.07
     ব্যক্তির
    -0.07
     menggunakan
    -0.07
     વ્યક્તિ
    -0.07
     encontraron
    -0.07
    บุคคล
    -0.06
    自分の
    -0.06
     individ
    -0.06
     gemacht
    -0.06
     ट्रेडिंग
    -0.06
    POSITIVE LOGITS
     ভালোবাসি
    0.06
    нта
    0.05
    偏差
    0.05
    仙台
    0.05
     delivery
    0.05
    抨
    0.05
    ivel
    0.05
    ánd
    0.05
     doped
    0.05
    Jon
    0.05
    Activations Density 0.033%

    No Known Activations