© 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. 10-GEMMASCOPE-RES-131K
    7. 61448
    Prev
    Next
    INDEX
    Explanations

    buy products in locations

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

    The neuron detects mentions of specific geographic place names.

    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
    🫀
    -1.57
     estadounid
    -1.55
    ⚢
    -1.55
     ſa
    -1.55
     tyl
    -1.53
     tivi
    -1.52
     darm
    -1.49
     mostrando
    -1.48
     moſt
    -1.48
    freund
    -1.47
    POSITIVE LOGITS
     that
    2.38
     those
    2.14
    Even
    1.78
     If
    1.73
     will
    1.72
     indicó
    1.71
    During
    1.68
     even
    1.67
    While
    1.66
    Those
    1.66
    Activations Density 0.006%

    No Known Activations