© 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. 19061
    Prev
    Next
    INDEX
    Explanations

    economic zone union pact

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

    The neuron detects mentions of formal EU or international policy/program titles and related trade/agreement terms (e.g. “Association Agreement,” “single market,” “free trade zone,” “Neighbourhood policy”).

    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
     Fácil
    -1.66
    険
    -1.50
     Acerca
    -1.50
     ještě
    -1.48
    Still
    -1.47
     Utilizamos
    -1.47
     jeugd
    -1.46
     chuť
    -1.39
     Ainda
    -1.38
     Obtén
    -1.38
    POSITIVE LOGITS
     my
    1.52
    A
    1.35
    其他
    1.28
    krankungen
    1.28
    h
    1.27
    "
    1.26
    E
    1.26
     different
    1.26
    setC
    1.24
    。（
    1.23
    Activations Density 0.016%

    No Known Activations