© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72672
    Prev
    Next
    INDEX
    Explanations

    neighboring places and people

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

    The neuron fires on mentions of neighbors or the concept of “neighborhood.”

    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
    idis
    -1.00
    "])
    -0.97
    dagog
    -0.96
    หล
    -0.94
    Montserrat
    -0.94
    éns
    -0.91
    Matchers
    -0.91
     occafion
    -0.90
    全国
    -0.89
     Odessa
    -0.88
    POSITIVE LOGITS
     neighbors
    1.72
     neighbor
    1.70
     neighbours
    1.60
     neighbour
    1.47
     Nachbarn
    1.21
     neighboring
    1.16
     Neighbors
    1.15
    neighbor
    1.14
    Neighbors
    1.13
     proximity
    1.11
    Activations Density 0.073%

    No Known Activations