© 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. 129916
    Prev
    Next
    INDEX
    Explanations

    describes, Note, or punctuation followed by article/number/U.S

    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
    modified
    -0.06
     我们
    -0.06
     አ
    -0.06
     modified
    -0.06
     redesigned
    -0.06
     iteratively
    -0.06
     adultos
    -0.06
     سعودی
    -0.06
     modi
    -0.06
     iterative
    -0.06
    POSITIVE LOGITS
     trước
    0.07
     ikke
    0.07
    三大
    0.06
     didn
    0.06
     হয়নি
    0.06
     called
    0.06
     rendszer
    0.06
     ఎక్కువగా
    0.06
     before
    0.06
    didn
    0.06
    Activations Density 0.009%

    No Known Activations