© 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. 110970
    Prev
    Next
    INDEX
    Explanations

    remote locations and arctic regions

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

    The neuron specializes in spotting capitalized tokens that are part of named entities (proper nouns).

    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
    ジアム
    -0.76
    clonal
    -0.73
    avao
    -0.73
    lismo
    -0.73
    ᓯ
    -0.72
     Ascent
    -0.70
    予
    -0.69
    JEL
    -0.69
    ituksen
    -0.68
    quantum
    -0.68
    POSITIVE LOGITS
     Arctic
    1.21
     fly
    1.12
    Arctic
    1.11
    northern
    1.07
     northern
    1.05
     Northern
    1.04
    Northern
    1.03
     Labrador
    1.03
     Inuit
    1.02
     Remote
    1.00
    Activations Density 0.037%

    No Known Activations