© 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. 129704
    Prev
    Next
    INDEX
    Explanations

    specific foreign words and proper nouns

    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
     صغير
    -0.06
     이미
    -0.06
     individual
    -0.06
     вже
    -0.06
    ত্তম
    -0.06
     schon
    -0.06
     Individual
    -0.06
    ^+$
    -0.06
     pequeño
    -0.06
     ‎
    -0.06
    POSITIVE LOGITS
     between
    0.07
     arasındaki
    0.07
     ट्रांस
    0.06
     that
    0.06
     interspersed
    0.06
    が変わ
    0.06
     graphically
    0.06
     Wadi
    0.06
    全新的
    0.06
     पै
    0.06
    Activations Density 0.001%

    No Known Activations