© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44622
    Prev
    Next
    INDEX
    Explanations

    provincial administrative terms

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on the word “provincial,” detecting mentions of provincial-level administrative units or the adjective “provincial.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵
    -3.16
     แต่
    -2.91
    因为
    -2.63
     ถ้า
    -2.45
     Además
    -2.42
     cuando
    -2.42
    不錯
    -2.38
     ไม่มี
    -2.30
     на
    -2.28
    睜
    -2.28
    POSITIVE LOGITS
    姈
    3.13
    .#
    3.02
    ization
    2.89
    .–
    2.88
     میشود
    2.81
    .=
    2.80
    .`
    2.80
    ܖ
    2.78
    ro
    2.75
    ized
    2.72
    Activations Density 0.004%

    No Known Activations