© 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. 22-GEMMASCOPE-RES-131K
    7. 40122
    Prev
    Next
    INDEX
    Explanations

    place names followed by divisions or institutions

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

    The neuron detects mentions of geographic place names (cities, regions, divisions, etc.).

    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
    Fitur
    -1.14
    凄く
    -1.09
    ߹
    -1.06
    innocent
    -1.03
    ヨーロ
    -1.02
     Главная
    -1.02
    essai
    -1.01
    なるべく
    -1.01
    salad
    -0.98
    Sculpture
    -0.98
    POSITIVE LOGITS
     its
    1.33
     their
    1.32
     you
    1.27
     branch
    1.23
     even
    1.12
     team
    1.07
     même
    1.03
     jego
    1.02
    Tran
    1.02
     page
    1.02
    Activations Density 0.085%

    No Known Activations