© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 437
    Prev
    Next
    INDEX
    Explanations

    street names and addresses

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

    The neuron fires on numeric tokens that represent street or location numbers in addresses (e.g. building or house numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ሳሪያ
    0.29
    📄
    0.28
     различи
    0.27
     pathophys
    0.26
    ℤ
    0.26
    SCHRAMM
    0.26
    🧑
    0.26
    studentRecord
    0.25
    📋
    0.25
     ডিজ
    0.25
    POSITIVE LOGITS
     Street
    0.55
     Boulevard
    0.51
     Blvd
    0.50
     Streets
    0.48
     boulevard
    0.48
     Road
    0.47
     Hwy
    0.46
     Lane
    0.46
     Avenue
    0.45
     street
    0.44
    Activations Density 0.193%

    No Known Activations