© 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. 119416
    Prev
    Next
    INDEX
    Explanations

    location administrative divisions

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

    The neuron strongly activates on common location‐description tokens (e.g. “in,” “the,” “Municipality,” “of”) used in geographic/administrative place entries.

    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
     vehemently
    -0.95
     might
    -0.95
     inadvertently
    -0.94
     weirdly
    -0.94
     makes
    -0.93
     secretly
    -0.92
     jokingly
    -0.91
     playfully
    -0.85
     expressly
    -0.85
     fascinating
    -0.85
    POSITIVE LOGITS
     gminy
    0.87
     accessibles
    0.83
     utilisés
    0.82
     minimale
    0.80
     miej
    0.80
    focused
    0.78
     quatre
    0.77
    demon
    0.76
    Tin
    0.76
    自分の
    0.76
    Activations Density 0.046%

    No Known Activations