© 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. 10-GEMMASCOPE-RES-131K
    4. 72984
    Prev
    Next
    INDEX
    Explanations

    place names and administrative divisions

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

    The neuron activates strongly on proper geographic location names (e.g., towns, regions, counties, mountains).

    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
    dő
    -1.40
     with
    -1.34
     will
    -1.32
     the
    -1.29
     what
    -1.28
    겟
    -1.17
     its
    -1.16
     similar
    -1.14
     pergunta
    -1.13
    EndPoint
    -1.13
    POSITIVE LOGITS
     zwier
    1.22
    
    1.20
     tył
    1.20
     sogen
    1.18
    THX
    1.17
     Seleccione
    1.16
    XVI
    1.16
     spezi
    1.13
     bañera
    1.13
     ''){
    1.09
    Activations Density 0.147%

    No Known Activations