© 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. 10-GEMMASCOPE-RES-131K
    4. 72967
    Prev
    Next
    INDEX
    Explanations

    dutch locations and professions

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

    The neuron fires strongly on place and landmark names (e.g., cities, metro stations, canals) in the text.

    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
    )
    -1.20
     such
    -1.19
     Sucher
    -1.12
     através
    -1.09
    шенный
    -1.09
     not
    -1.07
     Motorrad
    -1.06
     Logistik
    -1.05
     antonio
    -1.01
    comings
    -1.00
    POSITIVE LOGITS
    γωγ
    1.29
     esbo
    1.26
     cál
    1.25
    asyarakat
    1.23
     Países
    1.23
     vuestro
    1.16
     transportar
    1.13
    >(),
    1.13
     regulador
    1.13
    hijab
    1.11
    Activations Density 0.218%

    No Known Activations