© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 9820
    Prev
    Next
    INDEX
    Explanations

    North Carolina and North Dakota

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

    This neuron detects occurrences of the word “North,” principally in geographic 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_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
     
    -4.66
    ～～～～
    -2.97
    *
    -2.94
      
    -2.92
    <
    -2.89
    </strong>
    -2.84
    i
    -2.75
    g
    -2.55
    仿佛
    -2.52
    ーーーー
    -2.39
    POSITIVE LOGITS
    providedIn
    3.19
    逦
    3.09
     时尚
    2.89
    銑
    2.83
    ｘ
    2.80
     ハロウィン
    2.77
     []
    2.77
    ｇ
    2.69
    ｏ
    2.61
    镚
    2.56
    Activations Density 0.026%

    No Known Activations