© 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. 120968
    Prev
    Next
    INDEX
    Explanations

    cities and countries

    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
    前半
    -0.06
    ;
    -0.05
    4
    -0.05
    ther
    -0.05
    其他
    -0.05
    9
    -0.05
     bril
    -0.05
    3
    -0.05
     commence
    -0.05
    的其他
    -0.05
    POSITIVE LOGITS
     diferente
    0.07
     você
    0.07
    示例
    0.06
     개념
    0.06
    ție
    0.06
    ాత్ర
    0.06
     ayuda
    0.06
     pengertian
    0.06
     has
    0.06
     programm
    0.06
    Activations Density 0.014%

    No Known Activations