© 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. 71454
    Prev
    Next
    INDEX
    Explanations

    Hong Kong

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

    The main thing this neuron does is detect occurrences of the substring “Kong” in proper‐name contexts.

    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
    0
    -3.63
    1
    -3.17
    3
    -3.03
    7
    -2.73
    行って
    -2.67
    躄
    -2.66
    闼
    -2.63
    6
    -2.59
    谞
    -2.58
    也只是
    -2.52
    POSITIVE LOGITS
    s
    2.92
    –
    2.75
    ]
    2.73
    ‌هایی
    2.72
    \
    2.69
    י
    2.56
     are
    2.36
    颡
    2.33
    ी
    2.28
     है
    2.23
    Activations Density 0.003%

    No Known Activations