© 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. 118607
    Prev
    Next
    INDEX
    Explanations

    list of special characters, foreign words, and common words

    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
    某些
    -0.07
    也
    -0.06
    也都
    -0.06
     algunas
    -0.06
     also
    -0.06
    บาง
    -0.06
    一些
    -0.06
     certain
    -0.06
     كذلك
    -0.06
     larger
    -0.06
    POSITIVE LOGITS
    ☣
    0.07
     here
    0.06
     ruk
    0.06
    ämään
    0.06
     being
    0.06
     novamente
    0.06
     ought
    0.06
    뽁
    0.06
    在这里
    0.06
     Thane
    0.06
    Activations Density 0.004%

    No Known Activations