© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 38167
    Prev
    Next
    INDEX
    Explanations

    free trade agreements

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

    The neuron strongly responds to the multi-word heading “Facilitation of the entry into force of the EU-Ukraine Association Agreement (including a Deep and Comprehensive Free Trade Area)”, i.e. formal titles of legislative or treaty provisions.

    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
    constraint
    -0.79
    yah
    -0.73
    лення
    -0.73
     script
    -0.71
    psc
    -0.71
    gotoxy
    -0.71
     заказ
    -0.69
     berlina
    -0.69
     affid
    -0.69
    ubon
    -0.69
    POSITIVE LOGITS
     tariff
    1.68
     preferential
    1.61
     trade
    1.59
     Free
    1.49
     free
    1.44
     Tariff
    1.33
    Free
    1.31
    FTA
    1.30
     Trade
    1.30
    Trade
    1.27
    Activations Density 0.019%

    No Known Activations