© 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. 131022
    Prev
    Next
    INDEX
    Explanations

    programming languages and platforms

    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
     ধ্ব
    -0.07
     akan
    -0.06
    จะไม่
    -0.06
     cancelled
    -0.06
     không
    -0.06
     ไม่
    -0.06
     δεν
    -0.06
     לא
    -0.06
    Seperti
    -0.06
     además
    -0.06
    POSITIVE LOGITS
     one
    0.06
     which
    0.06
    ซึ่ง
    0.06
     یکی
    0.06
     wickedness
    0.06
     this
    0.06
    ுகிற
    0.06
    based
    0.06
     ఒకటి
    0.06
    ہ
    0.05
    Activations Density 0.048%

    No Known Activations