© 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. 1362
    Prev
    Next
    INDEX
    Explanations

    Syria, war, refugees, president

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

    The neuron consistently lights up on the word “Syrian” (and closely related Syria-derived country references).

    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
    玙
    -2.84
    漼
    -2.69
    铼
    -2.61
    昻
    -2.61
    谞
    -2.52
    ll
    -2.47
    鸶
    -2.45
    Ⲉ
    -2.41
    皞
    -2.41
    不过是
    -2.36
    POSITIVE LOGITS
    </b>
    3.02
    ка
    2.58
     {
    2.41
    鼉
    2.34
    ');
    2.34
     perfekte
    2.31
    苏联
    2.20
    两
    2.19
    孩子们
    2.16
    ");
    2.14
    Activations Density 0.003%

    No Known Activations