© 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. 118249
    Prev
    Next
    INDEX
    Explanations

    San Jose entities

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

    The neuron spikes on mentions of the city name “San José” (and closely related Bay Area place names like Santa Clara).

    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
     エンタメ
    -0.88
     Kars
    -0.82
     sno
    -0.80
    ientos
    -0.77
     Alfredo
    -0.76
     scones
    -0.75
     BBS
    -0.75
     _("
    -0.74
    adlo
    -0.73
    طل
    -0.73
    POSITIVE LOGITS
     Silicon
    1.41
    Silicon
    1.25
     SJ
    1.10
     silicon
    1.02
     Santa
    1.00
    Santa
    0.94
     Saratoga
    0.94
     Mercury
    0.93
    silicon
    0.92
     Cupertino
    0.91
    Activations Density 0.042%

    No Known Activations