© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49419
    Prev
    Next
    INDEX
    Explanations

    cities and towns

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

    This neuron detects tokens typical of place‐and location descriptions—e.g. words and names in structured geographic or administrative‐division 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
     проблемы
    -0.87
    pattern
    -0.79
    UY
    -0.78
    áculos
    -0.78
    ond
    -0.77
    scene
    -0.77
     hormones
    -0.76
    atio
    -0.76
    nées
    -0.75
    Local
    -0.75
    POSITIVE LOGITS
     city
    5.25
     City
    3.56
    city
    3.31
     città
    3.11
     town
    3.08
     cidade
    3.08
     ciudad
    3.02
     cities
    2.98
    City
    2.95
     города
    2.80
    Activations Density 0.111%

    No Known Activations