© 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. 118075
    Prev
    Next
    INDEX
    Explanations

    connects clauses or code blocks

    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
    この
    -0.07
     বিষয়টি
    -0.06
     this
    -0.06
    玻
    -0.06
     VII
    -0.06
     জ্ঞানী
    -0.06
     我
    -0.05
     ব্যাপারটা
    -0.05
     この
    -0.05
     संपन्न
    -0.05
    POSITIVE LOGITS
     exhort
    0.07
     że
    0.07
     اسماع
    0.06
    ዋ
    0.06
    দেখিতে
    0.06
    Alongside
    0.06
     فونبیٹ
    0.06
     asem
    0.06
    ：“
    0.06
     estimular
    0.06
    Activations Density 0.044%

    No Known Activations