© 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. 34-GEMMASCOPE-RES-131K
    7. 83183
    Prev
    Next
    INDEX
    Explanations

    against certain countries

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

    This neuron selectively activates on tokens in the very first (lead) sentence of a news‐style article.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    US
    -0.86
     آمریکا
    -0.82
     شناسی
    -0.80
     US
    -0.79
     американ
    -0.77
     alphabe
    -0.75
     coloriage
    -0.75
     barrica
    -0.74
     AMERICAN
    -0.74
    lew
    -0.74
    POSITIVE LOGITS
     China
    3.03
     Russia
    2.88
     Iran
    2.67
     Chinese
    2.42
     Russian
    2.34
    China
    2.27
    Russia
    2.05
     Cuba
    1.95
     Iranian
    1.95
    Iran
    1.91
    Activations Density 0.051%

    No Known Activations