© 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. 104976
    Prev
    Next
    INDEX
    Explanations

    geographic entities and specific locations

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

    This neuron detects references to South Sudan–related legal or administrative entities (e.g., nationality law, citizenship, counties).

    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
     简介
    -1.26
    ització
    -1.17
    Litteratur
    -1.16
     parfums
    -1.15
    ífer
    -1.14
     permettent
    -1.13
    ICLE
    -1.10
     também
    -1.10
     notícia
    -1.10
     समीक्षक
    -1.09
    POSITIVE LOGITS
     sustainable
    1.16
     who
    1.13
     recent
    1.09
     whose
    1.07
     úl
    1.06
     šo
    1.05
     will
    1.05
    koc
    1.03
    和大
    1.03
    ughty
    1.03
    Activations Density 0.035%

    No Known Activations