© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68441
    Prev
    Next
    INDEX
    Explanations

    North American

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

    The neuron flags references to North America (e.g. “North American,” “North America,” or related variants).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    8
    -2.75
    -"
    -2.72
    }
    -2.67
    ("
    -2.48
    1
    -2.47
    7
    -2.42
     può
    -2.30
    ="
    -2.28
    6
    -2.28
    <
    -2.27
    POSITIVE LOGITS
    笵
    2.05
     その
    2.05
    卹
    2.03
    ઁ
    2.03
    柺
    2.03
     refroidissement
    1.97
    เกง
    1.97
    нных
    1.91
    咯
    1.88
    刳
    1.88
    Activations Density 0.016%

    No Known Activations