© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 116087
    Prev
    Next
    INDEX
    Explanations

    non-english words and symbols

    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
    Negative Logits
     sowas
    -0.06
     cursory
    -0.06
     expressing
    -0.06
    ressione
    -0.06
    satunya
    -0.06
    昰
    -0.06
     चर
    -0.06
     normal
    -0.06
    ಡುಗೆ
    -0.06
    iteness
    -0.06
    POSITIVE LOGITS
    が悪
    0.07
     согласо
    0.07
     which
    0.06
    fusc
    0.06
    ප
    0.06
     którą
    0.06
     හා
    0.05
     غلط
    0.05
     Dac
    0.05
     Debra
    0.05
    Activations Density 0.006%

    No Known Activations