© 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. 118303
    Prev
    Next
    INDEX
    Explanations

    country codes and abbreviations

    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
     myös
    -0.06
     egy
    -0.06
     Também
    -0.06
    ㄳ
    -0.06
     Tiene
    -0.06
    kości
    -0.06
     både
    -0.06
     गठित
    -0.06
    También
    -0.06
     sẽ
    -0.06
    POSITIVE LOGITS
     такое
    0.06
     игры
    0.06
    reduction
    0.06
     ऐसा
    0.06
    persons
    0.06
    Use
    0.05
     games
    0.05
     twitter
    0.05
     tricks
    0.05
     네
    0.05
    Activations Density 0.002%

    No Known Activations