© 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. 131049
    Prev
    Next
    INDEX
    Explanations

    html title tags

    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
    寻找
    -0.07
     není
    -0.06
    தாகும்
    -0.06
     ergeben
    -0.06
     কাবুল
    -0.06
     থাকিলে
    -0.06
     proclaiming
    -0.06
     بدء
    -0.06
     വഹ
    -0.06
     срок
    -0.06
    POSITIVE LOGITS
     ht
    0.06
    岀
    0.06
     erection
    0.05
    也
    0.05
     Eintritt
    0.05
     manufacture
    0.05
     knitted
    0.05
     erected
    0.05
     ७
    0.05
     createdAt
    0.05
    Activations Density 0.002%

    No Known Activations