© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 12051
    Prev
    Next
    INDEX
    Explanations

    complexity, safety

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

    The neuron strongly activates on geographic references—that is, place names and location mentions.

    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_24_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
    0.83
    го
    0.75
    体制
    0.74
    摘要
    0.72
    家用
    0.70
    و
    0.70
    0.67
     esclusivamente
    0.66
    Przyp
    0.66
    0.64
    POSITIVE LOGITS
     knack
    0.87
     grime
    0.86
     Cádiz
    0.84
     gründ
    0.81
    кает
    0.80
    бры
    0.79
     frustrating
    0.77
     Princes
    0.77
     WIP
    0.77
     disgusting
    0.76
    Activations Density 0.000%

    No Known Activations