© 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. 118664
    Prev
    Next
    INDEX
    Explanations

    foreign or diverse origins

    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
     этом
    -0.07
     này
    -0.07
     acest
    -0.07
     diesem
    -0.06
     această
    -0.06
     adorable
    -0.06
     این
    -0.06
     nineteen
    -0.06
     this
    -0.06
     tomto
    -0.06
    POSITIVE LOGITS
     different
    0.08
     différentes
    0.07
     differing
    0.07
     farklı
    0.07
     différente
    0.07
    不同的
    0.07
     diferentes
    0.07
    different
    0.06
     diferite
    0.06
     différents
    0.06
    Activations Density 0.001%

    No Known Activations