© 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. 130186
    Prev
    Next
    INDEX
    Explanations

    locations followed by cities or place 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
     Reasonable
    -0.07
    价格
    -0.07
     않고
    -0.06
     만나
    -0.06
     가격
    -0.06
    價格
    -0.06
     Comfortable
    -0.06
     মূল্য
    -0.06
    的价格
    -0.06
    ᄆ
    -0.06
    POSITIVE LOGITS
    Already
    0.06
     enrolling
    0.06
     schon
    0.06
     nations
    0.06
    qual
    0.06
     patriotic
    0.06
     galactic
    0.06
     aviation
    0.06
     already
    0.06
    ;#
    0.06
    Activations Density 0.028%

    No Known Activations