© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7094
    Prev
    Next
    INDEX
    Explanations

    Turkey and Turkish

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

    The neuron is strongly activated by multiword capitalized names and titles (e.g. organizations, initiatives, proper nouns).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     американ
    0.89
     Джон
    0.89
    ோவின்
    0.88
     Джор
    0.86
    輥
    0.86
     Австра
    0.84
    ビーチ
    0.84
     アメリカ
    0.80
    американ
    0.80
     Великобритании
    0.80
    POSITIVE LOGITS
     İstanbul
    2.13
     Türkiye
    2.06
     Turkish
    2.00
     Atatürk
    2.00
     Ankara
    1.97
    Türkiye
    1.94
     İzmir
    1.93
    İstanbul
    1.93
    Turkish
    1.92
     İ
    1.91
    Activations Density 0.104%

    No Known Activations