© 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. 34-GEMMASCOPE-RES-131K
    7. 65977
    Prev
    Next
    INDEX
    Explanations

    Japanese place names and geography

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

    The neuron fires on occurrences of Japanese geographic place names (cities, districts, lakes, prefectures, etc.).

    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
     일본
    -1.30
    japanese
    -1.24
     japanese
    -1.22
    日本人
    -1.13
     Japanese
    -1.12
     япон
    -1.10
    Japanese
    -1.05
    JAPAN
    -1.02
     japan
    -1.00
     ژاپ
    -0.98
    POSITIVE LOGITS
     Okay
    1.20
     mountain
    0.81
     no
    0.81
     Hotspur
    0.80
     pine
    0.79
     hydraulic
    0.79
     Hig
    0.79
     Ok
    0.78
     −
    0.77
     climbing
    0.77
    Activations Density 0.039%

    No Known Activations