© 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. 105415
    Prev
    Next
    INDEX
    Explanations

    city names and locations

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

    The neuron is activated by mentions of specific geographic place names (e.g., Indian city/locality names like Gurgaon, Noida, MG Road).

    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
    
    -1.52
    。】
    -1.52
    ！』
    -1.51
    是
    -1.45
     maleta
    -1.45
    鄚
    -1.41
    。』
    -1.40
     BaseEntity
    -1.39
     fenti
    -1.38
     Starring
    -1.36
    POSITIVE LOGITS
     of
    2.00
    ↵↵
    1.96
    .
    1.73
     neuen
    1.50
     \
    1.47
    ⅝
    1.41
    ⅜
    1.41
     ]
    1.41
     sechs
    1.40
     The
    1.39
    Activations Density 0.011%

    No Known Activations