© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 28393
    Prev
    Next
    INDEX
    Explanations

    geographic coordinates and latitude/longitude

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

    The neuron fires on numeric tokens in geographic coordinate and location data, such as latitude/longitude measurements.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     surabaya
    -1.35
    ventes
    -1.30
     bambu
    -1.28
    jadikan
    -1.27
     sepatu
    -1.25
     bogor
    -1.24
    petite
    -1.23
    tricks
    -1.23
     bekasi
    -1.23
    泐
    -1.22
    POSITIVE LOGITS
    le
    1.18
    o
    1.11
    aw
    1.09
    ol
    1.09
    j
    1.09
    mə
    1.07
     Candida
    1.07
    ual
    1.07
    ic
    1.05
    l
    1.05
    Activations Density 0.009%

    No Known Activations