© 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. 7814
    Prev
    Next
    INDEX
    Explanations

    Ukrainian or UK location

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

    The neuron strongly activates on country‐code abbreviations (e.g. “UK,” “USA”).

    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
    ATION
    0.68
     मिल्
    0.65
     آمریک
    0.65
    ઓને
    0.64
     przyczyn
    0.60
     程
    0.58
     Lâm
    0.57
    Flicky
    0.55
     الأمريكية
    0.55
    美国
    0.55
    POSITIVE LOGITS
    rainian
    0.93
    raine
    0.79
    ्रेन
    0.75
     Uk
    0.70
     Isles
    0.68
    RAIN
    0.67
    ὺ
    0.66
    ulele
    0.64
    েন
    0.61
    raines
    0.61
    Activations Density 0.118%

    No Known Activations