© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 120647
    Prev
    Next
    INDEX
    Explanations

    special characters and multilingual text

    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
    immediately
    -0.06
     imediatamente
    -0.06
    後に
    -0.06
    ↴
    -0.06
    转化
    -0.06
     immediately
    -0.06
    Ü
    -0.06
     transforme
    -0.06
     Indexed
    -0.06
    icago
    -0.06
    POSITIVE LOGITS
     that
    0.08
     cung
    0.07
    自己
    0.06
     spiega
    0.06
     svak
    0.06
     such
    0.06
    궁
    0.06
     சற்று
    0.06
    ठी
    0.06
     Sam
    0.05
    Activations Density 0.004%

    No Known Activations