© 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. 130744
    Prev
    Next
    INDEX
    Explanations

    dates and locations

    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
     tomto
    -0.07
     цю
    -0.06
     অঞ্চ
    -0.06
     Mika
    -0.06
     मिश
    -0.06
    وید
    -0.06
    整個
    -0.06
    苌
    -0.06
     น่ะ
    -0.06
    OGRAP
    -0.06
    POSITIVE LOGITS
    Here
    0.06
    There
    0.06
    用意
    0.06
     
    0.06
     की
    0.06
    ش
    0.05
    运
    0.05
     has
    0.05
     reporters
    0.05
     দেওয়া
    0.05
    Activations Density 0.001%

    No Known Activations