© 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. 34-GEMMASCOPE-RES-131K
    7. 30515
    Prev
    Next
    INDEX
    Explanations

    Hawaii and Honolulu

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

    The main thing this neuron does is pick out Hawaiian place and institution names (proper nouns tied to locations in Hawaii).

    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
     Amish
    -0.96
     riverside
    -0.90
     arma
    -0.87
    博多
    -0.86
     Bayou
    -0.85
     katun
    -0.83
     tuli
    -0.82
     Loon
    -0.82
    viewDidLoad
    -0.81
     kd
    -0.81
    POSITIVE LOGITS
     Hawaii
    2.17
    Hawaii
    1.88
     Hawaiian
    1.80
     Honolulu
    1.80
     Hawai
    1.72
     Oahu
    1.66
    hawaii
    1.55
    ʻ
    1.54
     Maui
    1.49
    Honolulu
    1.42
    Activations Density 0.072%

    No Known Activations