© 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. 129814
    Prev
    Next
    INDEX
    Explanations

    city/region names

    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
     pertama
    -0.07
     first
    -0.07
     первый
    -0.06
     Indonesian
    -0.06
     decide
    -0.06
     takes
    -0.06
     MDR
    -0.06
     ceases
    -0.05
    第一个
    -0.05
     ছিলোনা
    -0.05
    POSITIVE LOGITS
     buena
    0.07
     कानूनों
    0.06
     gjennom
    0.06
     into
    0.06
     वैसे
    0.06
     गोप
    0.06
     এখান
    0.06
     genom
    0.06
    ব্লিউ
    0.06
    筈
    0.06
    Activations Density 0.012%

    No Known Activations