© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 2368
    Prev
    Next
    INDEX
    Explanations

    Greenland, Inuit, Arctic

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

    This neuron fires on proper‐name tokens—especially geographic/place names (and related named entities, including years).

    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
    laterra
    -0.82
    Katy
    -0.79
     Waikato
    -0.78
    ᔪ
    -0.77
    ᓐ
    -0.74
    벗
    -0.74
     Croatian
    -0.73
     bean
    -0.70
    uF
    -0.69
     inflationary
    -0.68
    POSITIVE LOGITS
     Eskimo
    1.72
     Greenland
    1.58
     Inuit
    1.52
     Arctic
    1.44
    Arctic
    1.33
     Alaska
    1.20
    Esk
    1.16
     Esk
    1.04
    arctic
    1.04
     Thule
    1.02
    Activations Density 0.017%

    No Known Activations