© 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. 10-GEMMASCOPE-RES-131K
    7. 70768
    Prev
    Next
    INDEX
    Explanations

    European Union and related entities

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

    The neuron activates on occurrences of “European” (e.g., as part of organization or region names).

    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
    \
    -3.45
     
    -2.80
     The
    -2.58
     può
    -2.58
    可以
    -2.45
    '
    -2.41
    ".
    -2.38
    絎
    -2.36
    有很多
    -2.25
     Your
    -2.20
    POSITIVE LOGITS
    鈊
    3.09
    ୌ
    2.91
    ઁ
    2.86
    沇
    2.81
    )،
    2.78
    呖
    2.69
    ꦠ
    2.66
     zusätz
    2.64
     exquisite
    2.59
    觏
    2.48
    Activations Density 0.007%

    No Known Activations