© 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. 130208
    Prev
    Next
    INDEX
    Explanations

    prevent

    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
    讓人
    -0.07
     完成
    -0.07
     этого
    -0.07
     लोकार्
    -0.07
     luar
    -0.07
    经过
    -0.06
     not
    -0.06
     ಮೂಲಕ
    -0.06
     reticulum
    -0.06
    让人
    -0.06
    POSITIVE LOGITS
    3
    0.06
     establishments
    0.06
    如何
    0.06
    5
    0.06
     austere
    0.05
    7
    0.05
     대해
    0.05
    6
    0.05
     countries
    0.05
    8
    0.05
    Activations Density 0.013%

    No Known Activations