© 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. 116591
    Prev
    Next
    INDEX
    Explanations

    Colchester, Essex places

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

    The neuron strongly activates on capitalized proper‐noun tokens—especially place and organization names.

    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
     Bangalore
    -0.76
     Bavarian
    -0.76
    egl
    -0.75
     Alabama
    -0.74
     Gohan
    -0.71
     Кры
    -0.70
    llingen
    -0.69
    多摩
    -0.68
     SQLite
    -0.68
    Кры
    -0.68
    POSITIVE LOGITS
     Essex
    2.19
    Essex
    1.92
     Colchester
    1.69
     Brentwood
    1.27
     Harlow
    1.16
    essex
    1.16
     Rayleigh
    0.96
    千葉
    0.94
     千葉
    0.93
     Chel
    0.91
    Activations Density 0.023%

    No Known Activations