© 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. 103433
    Prev
    Next
    INDEX
    Explanations

    regions, provinces, oblasts

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

    The neuron detects named geopolitical or administrative region labels (e.g. province, oblast, region names).

    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
    btnDelete
    -0.81
     フォント
    -0.81
    Brains
    -0.78
    챠
    -0.76
     CAPS
    -0.75
    izoen
    -0.74
    huizen
    -0.73
    NAG
    -0.73
    AGI
    -0.73
     シルエット
    -0.73
    POSITIVE LOGITS
     region
    4.03
     Region
    3.97
    Region
    3.75
    region
    3.63
     regions
    3.33
    regions
    3.05
    REGION
    3.00
     REGION
    3.00
     Regions
    2.94
     regional
    2.89
    Activations Density 0.030%

    No Known Activations