© 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. 60271
    Prev
    Next
    INDEX
    Explanations

    exotic and oriental things

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

    This neuron spotlights exotic or Orientalist cultural terms and foreign-place proper names (e.g. “exoticism,” “Orientalism,” “Szymanowski,” “Stamboul”).

    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
     eko
    -0.89
     argent
    -0.89
     kanker
    -0.86
    嗪
    -0.86
     Olimp
    -0.85
     poliuret
    -0.85
     Finlandia
    -0.85
     olimp
    -0.84
     Québec
    -0.82
     android
    -0.81
    POSITIVE LOGITS
     exotic
    3.19
    exotic
    2.88
     Exotic
    2.72
    Exotic
    2.59
     exo
    2.14
    exo
    1.68
     Oriental
    1.60
     oriental
    1.52
     Exo
    1.48
     foreign
    1.46
    Activations Density 0.062%

    No Known Activations