© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99021
    Prev
    Next
    INDEX
    Explanations

    NYC boroughs and associated places

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

    The neuron strongly activates on named geographic locations (e.g. place names like Brooklyn Park, Manhattan College, Bronx Park).

    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
     insuper
    -0.84
    ležité
    -0.82
     amal
    -0.79
     sydney
    -0.79
     Mesopo
    -0.78
     كه
    -0.77
    🫐
    -0.77
     prevista
    -0.76
    erro
    -0.76
     corsair
    -0.75
    POSITIVE LOGITS
     borough
    1.36
     Borough
    1.20
     Bridge
    1.05
    henge
    1.01
    宴会
    0.93
     prosecutors
    0.92
    ilda
    0.90
     ilç
    0.90
    Vegan
    0.83
    熾
    0.83
    Activations Density 0.014%

    No Known Activations