© 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. 71133
    Prev
    Next
    INDEX
    Explanations

    toponymic locations

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

    The neuron activates on subword pieces of proper nouns denoting place names or institutions.

    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
    
    -1.61
    龱
    -1.55
    Paket
    -1.54
    ྥ
    -1.49
     outras
    -1.48
    ebenarnya
    -1.48
    tedrale
    -1.47
    が欲しい
    -1.46
     divertido
    -1.45
    Kanal
    -1.45
    POSITIVE LOGITS
    of
    2.13
    al
    2.06
    t
    2.03
    el
    1.85
    inemann
    1.84
    e
    1.73
    ",
    1.73
    la
    1.70
    <strong>
    1.69
    at
    1.66
    Activations Density 0.782%

    No Known Activations