© 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. 123553
    Prev
    Next
    INDEX
    Explanations

    miami-dade county and locations

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

    The neuron strongly responds to place names and geographic entities—especially references to Miami and its surrounding locations.

    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
    an
    -1.87
    4
    -1.75
    '
    -1.73
    τας
    -1.70
    有助
    -1.50
    n
    -1.44
    ity
    -1.43
    it
    -1.41
    out
    -1.41
    ("")]
    -1.38
    POSITIVE LOGITS
    Miami
    1.76
    釙
    1.52
     Miami
    1.51
     vodou
    1.49
    甞
    1.47
     capuz
    1.45
    attacks
    1.42
     europé
    1.41
     brinquedo
    1.41
    ciles
    1.41
    Activations Density 0.023%

    No Known Activations