© 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. 117919
    Prev
    Next
    INDEX
    Explanations

    as it is

    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
     निरीक्षक
    -0.06
     योद्धा
    -0.06
     very
    -0.06
     morbid
    -0.06
     ব্যতীত
    -0.06
    translator
    -0.06
     সার্ভিস
    -0.06
     hillside
    -0.06
     اجمعين
    -0.05
     মৃদু
    -0.05
    POSITIVE LOGITS
     ಇ
    0.06
     podría
    0.06
     certains
    0.06
    ס
    0.06
     debería
    0.06
     conceitos
    0.06
     jelent
    0.06
     Carter
    0.06
     denna
    0.06
     बिजली
    0.06
    Activations Density 0.018%

    No Known Activations