© 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. 34-GEMMASCOPE-RES-131K
    7. 93227
    Prev
    Next
    INDEX
    Explanations

    Virginia places and organizations

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

    The neuron strongly activates on location‐indicating language—place names (e.g. Reston, Dulles, Town Center) and the prepositions (in, on, off, to) that mark where something is.

    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
    ListBy
    -0.81
    ակ
    -0.76
     DOB
    -0.75
     appendages
    -0.73
    astar
    -0.73
    quants
    -0.72
    resultCode
    -0.72
     nth
    -0.71
     tuss
    -0.71
     CentOS
    -0.68
    POSITIVE LOGITS
     Fairfax
    0.81
     vekt
    0.74
     murmuring
    0.71
     Station
    0.70
     espl
    0.70
    온
    0.70
     iné
    0.69
    lesen
    0.67
     Corinthians
    0.66
     Corporations
    0.66
    Activations Density 0.029%

    No Known Activations