© 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. 55731
    Prev
    Next
    INDEX
    Explanations

    Lincoln (people, places, institutions)

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

    The main thing this neuron does is detect occurrences of the proper name “Lincoln” (and closely associated capitalized tokens).

    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
    WT
    -0.82
     Hernández
    -0.77
     eleições
    -0.76
     krep
    -0.73
    ловая
    -0.72
    編曲
    -0.71
    ##
    -0.71
    🍥
    -0.70
    unlike
    -0.69
     lact
    -0.69
    POSITIVE LOGITS
     Lincoln
    1.30
    Lincoln
    1.16
     lincoln
    1.07
    coln
    0.95
     LINCOLN
    0.94
     Gettysburg
    0.93
     LN
    0.93
     Lincolnshire
    0.87
     Nebraska
    0.80
     لينك
    0.80
    Activations Density 0.027%

    No Known Activations