© 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. 4177
    Prev
    Next
    INDEX
    Explanations

    virginia cities and regions

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

    The neuron strongly activates on mentions of Virginia place names or datelines (e.g. “VIRGINIA,” “Norfolk,” “Virginia Beach,” etc.).

    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
     vineyards
    -0.72
    聾
    -0.71
    didSet
    -0.70
     mlu
    -0.70
     relacion
    -0.70
     upstream
    -0.70
     szere
    -0.69
    InputStream
    -0.69
    спу
    -0.69
    asjoner
    -0.69
    POSITIVE LOGITS
     Norfolk
    1.60
    Norfolk
    1.44
     Chesapeake
    1.30
     Virginia
    1.28
    Virginia
    1.15
     VIRGINIA
    1.05
     Portsmouth
    0.98
     Hampton
    0.94
     Neptune
    0.94
     HRT
    0.92
    Activations Density 0.019%

    No Known Activations