© 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. 34729
    Prev
    Next
    INDEX
    Explanations

    historical and cultural groups

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

    The neuron responds strongly to geographic and geopolitical terms—names of regions or broad place descriptors (e.g. Europe, Western, World, colonial, Ottoman, Asian).

    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
    萊
    -0.81
     neoliberal
    -0.79
    umm
    -0.79
     Morgen
    -0.76
    umman
    -0.76
    国会
    -0.75
     elett
    -0.75
    لر
    -0.73
     fichero
    -0.72
     elekt
    -0.71
    POSITIVE LOGITS
     Eurasian
    1.07
     Eurasia
    1.04
    inerario
    0.96
     societies
    0.85
     Empires
    0.82
    ListTile
    0.81
    Diffusion
    0.81
     coercive
    0.78
    itzen
    0.77
    Tribute
    0.77
    Activations Density 0.019%

    No Known Activations