© 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. 130707
    Prev
    Next
    INDEX
    Explanations

    data and international legislation

    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
    常見
    -0.07
     aftermath
    -0.07
     знамени
    -0.06
     mortality
    -0.06
     практика
    -0.06
    7
    -0.06
     уника
    -0.06
    がたくさん
    -0.06
     тради
    -0.06
     accidentally
    -0.06
    POSITIVE LOGITS
     با
    0.07
     =
    0.07
     به
    0.07
    الا
    0.07
     data
    0.06
     কোনো
    0.06
    HI
    0.06
    data
    0.05
     आपला
    0.05
     ا
    0.05
    Activations Density 0.045%

    No Known Activations