© 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. 69221
    Prev
    Next
    INDEX
    Explanations

    place name disambiguation

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

    The neuron flags capitalized multi-token place names (towns, cities, or other geographic entity names).

    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
    -1.97
     more
    -1.52
     not
    -1.48
     about
    -1.46
     köpa
    -1.32
     the
    -1.28
     now
    -1.28
     However
    -1.17
     använda
    -1.16
     When
    -1.15
    POSITIVE LOGITS
    🕗
    1.34
    注意点
    1.32
    ゚
    1.26
     jego
    1.24
     его
    1.20
     silencioso
    1.19
    ciptakan
    1.17
    SFER
    1.17
    Its
    1.16
    嬉しいです
    1.16
    Activations Density 0.095%

    No Known Activations