© 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. 50178
    Prev
    Next
    INDEX
    Explanations

    New Jersey locations

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

    The neuron strongly activates on proper-noun tokens naming places, street addresses, and organizational 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_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
    Finishing
    -0.71
    chuk
    -0.71
    chaffen
    -0.71
    かっこ
    -0.71
     Telerik
    -0.70
     allons
    -0.69
    iferous
    -0.68
     sê
    -0.68
     argued
    -0.68
    ),"
    -0.68
    POSITIVE LOGITS
     Hoboken
    1.63
     Jersey
    1.05
    Hudson
    1.02
     Hudson
    0.97
    Jersey
    0.91
    تع
    0.84
     PATH
    0.82
     Bergen
    0.82
    PATH
    0.81
     hudson
    0.81
    Activations Density 0.023%

    No Known Activations