© 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. 10-GEMMASCOPE-RES-131K
    7. 99573
    Prev
    Next
    INDEX
    Explanations

    street locations and events

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

    The neuron strongly activates on mentions of specific street or place names and related location references (e.g. “Hollywood Blvd,” “Main Street,” “downtown,” “tourists on …”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     then
    -1.38
     campionato
    -1.16
     use
    -1.16
     Kühlschrank
    -1.14
     them
    -1.13
     they
    -1.12
     infek
    -1.12
     insegu
    -1.10
     località
    -1.10
     dovr
    -1.09
    POSITIVE LOGITS
     urbanas
    1.18
     whatnot
    1.11
     itens
    1.11
     comerciales
    1.05
     vectoriales
    1.04
    了一会儿
    1.04
    滓
    1.02
     zagran
    1.01
     sowohl
    1.01
     tir
    1.01
    Activations Density 0.103%

    No Known Activations