© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 131052
    Prev
    Next
    INDEX
    Explanations

    Hong Kong

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

    The neuron is triggered by mentions of “Hong Kong” (the location name) in the text.

    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
    ɱ
    -1.25
    schon
    -1.21
     puasa
    -1.20
     fermo
    -1.20
    filtro
    -1.17
     pertama
    -1.16
     yh
    -1.15
    Codigo
    -1.15
     obiet
    -1.13
    デメリット
    -1.13
    POSITIVE LOGITS
     generando
    1.30
     who
    1.27
    香港
    1.20
     Dingen
    1.13
     darunter
    1.11
    ご覧
    1.10
     impress
    1.10
     munt
    1.09
    上了
    1.05
    Until
    1.05
    Activations Density 0.057%

    No Known Activations