© 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. 99602
    Prev
    Next
    INDEX
    Explanations

    entrepreneurial, dependency, DUI

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

    This neuron detects abstract noun or adjective forms marked by suffixes like “-ial” or “-ency” (e.g. entrepreneurial, dependency).

    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
    籏
    -2.75
    琑
    -2.64
    挣
    -2.48
    屨
    -2.47
     bús
    -2.45
    慙
    -2.45
    та
    -2.44
    锖
    -2.39
    ܆
    -2.34
     två
    -2.33
    POSITIVE LOGITS
    ."
    2.61
    地看着
    2.56
     or
    2.38
    倨
    2.30
     for
    2.27
    autogui
    2.27
    )
    2.25
    得好
    2.25
     over
    2.23
    旅程
    2.22
    Activations Density 0.005%

    No Known Activations