© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 34851
    Prev
    Next
    INDEX
    Explanations

    Senegal and Dakar

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

    The neuron fires on capitalized tokens that are part of named entities—e.g. place names, personal names, dates, or other proper nouns.

    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
     Richmond
    -0.75
     cocoa
    -0.75
     matemáticas
    -0.74
     valt
    -0.73
    obot
    -0.72
    grown
    -0.71
    vae
    -0.71
    orous
    -0.70
     Quan
    -0.69
     Schul
    -0.69
    POSITIVE LOGITS
     Senegal
    1.77
     Sene
    1.64
    Senegal
    1.45
     Dakar
    1.40
     sene
    1.02
    🇸
    1.01
     Ndi
    0.90
     Sénégal
    0.87
    sene
    0.87
     Mame
    0.77
    Activations Density 0.032%

    No Known Activations