© 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. 34-GEMMASCOPE-RES-131K
    7. 81575
    Prev
    Next
    INDEX
    Explanations

    place names followed by located

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

    The neuron fires on the core “X is a Y” definitional construction—identifying the copula (“is a”) and the immediate noun phrase that follows.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     distintos
    -1.02
     distintas
    -0.95
    itel
    -0.86
    adell
    -0.81
    gusted
    -0.81
    iettivo
    -0.80
     everywhere
    -0.80
    ::*;
    -0.79
    colorPrimary
    -0.79
     intorno
    -0.78
    POSITIVE LOGITS
     located
    7.59
    Located
    5.78
    located
    5.59
     Located
    5.56
     situated
    5.38
     situé
    4.41
    位于
    4.16
     située
    3.98
     расположен
    3.81
     ubicada
    3.77
    Activations Density 0.428%

    No Known Activations