© 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. 10-GEMMASCOPE-RES-131K
    7. 8339
    Prev
    Next
    INDEX
    Explanations

    city, county, ocean, tsunami

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

    The neuron fires on geographic-location words—especially the token “City” (e.g. in “Oklahoma City,” “Iowa City”) and similar place‐name terms.

    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
     It
    -2.34
    of
    -2.30
     -
    -2.22
     do
    -2.22
     t
    -2.20
    T
    -2.20
     quaint
    -2.06
     humorous
    -1.92
    ="
    -1.91
     Of
    -1.90
    POSITIVE LOGITS
     撮っ
    2.34
    읗
    2.00
     *>
    2.00
    ꯳
    1.96
     vmax
    1.88
    ندن
    1.80
     hii
    1.77
    讎
    1.75
     広場
    1.74
     teile
    1.70
    Activations Density 0.003%

    No Known Activations