© 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. 66900
    Prev
    Next
    INDEX
    Explanations

    fort lauderdale & florida

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

    The neuron strongly activates on place names (especially city or county names, e.g. Fort Lauderdale, Broward County, Pompano Beach).

    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
    as
    -1.95
    じゃあ
    -1.59
    又は
    -1.59
    raten
    -1.55
    Подготовка
    -1.52
     savory
    -1.51
    توض
    -1.48
     мое
    -1.48
     végétale
    -1.48
    してます
    -1.47
    POSITIVE LOGITS
    $
    2.14
    ”,
    1.98
    ,“
    1.85
     burch
    1.81
     xxv
    1.78
     hecta
    1.72
     xxiii
    1.66
     главным
    1.66
     vorgenommen
    1.65
    鹇
    1.65
    Activations Density 0.006%

    No Known Activations