© 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. 23924
    Prev
    Next
    INDEX
    Explanations

    Austria and Austrian places

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

    The neuron strongly activates on capitalized named entities—especially organization and agency names (often containing “Vienna”) and formal place‐name references.

    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
    Deutschland
    -0.81
     nebst
    -0.80
    Stiftung
    -0.79
     Schwal
    -0.78
     Jacksonville
    -0.78
     Farmington
    -0.78
    Jacksonville
    -0.78
    Yale
    -0.77
     Björn
    -0.76
    Maryland
    -0.73
    POSITIVE LOGITS
     Austria
    3.03
     Austrian
    3.00
     Vienna
    2.86
    Austria
    2.48
    Vienna
    2.31
     ав
    1.91
    Aust
    1.90
    Autriche
    1.82
     österreich
    1.82
     Ав
    1.78
    Activations Density 0.083%

    No Known Activations