© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 87020
    Prev
    Next
    INDEX
    Explanations

    Hong Kong Chief Executive

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

    The neuron strongly fires on tokens that come from a structured infobox or table header (e.g. labels and titles in a wiki-style sidebar).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ignment
    -0.82
    ANTS
    -0.70
    isiones
    -0.68
     dirait
    -0.68
    izados
    -0.68
    striping
    -0.67
     distribution
    -0.67
    っているので
    -0.67
     envoyer
    -0.66
    rabbitmq
    -0.66
    POSITIVE LOGITS
     Hong
    1.77
    Hong
    1.52
     香港
    1.52
     SAR
    1.41
    SAR
    1.34
     HK
    1.23
    香港
    1.22
     Hongkong
    1.20
    HK
    1.20
     hong
    1.04
    Activations Density 0.022%

    No Known Activations