© 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. 105220
    Prev
    Next
    INDEX
    Explanations

    Saudi Arabia and associates

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

    The neuron strongly activates on mentions of Saudi Arabia and its related geographic or political proper names (e.g. Riyadh, Gulf states, Middle East).

    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
     Then
    -1.55
    ,"
    -1.48
    м
    -1.47
    ."
    -1.45
    سجيلات
    -1.43
    #"
    -1.42
     That
    -1.41
    ]
    -1.40
     Its
    -1.38
     coincident
    -1.38
    POSITIVE LOGITS
     dönd
    1.55
    栊
    1.41
    ί
    1.41
     infolge
    1.40
    YOUR
    1.39
     doua
    1.39
    🐮
    1.38
    czenia
    1.38
    돛
    1.38
    餮
    1.37
    Activations Density 0.017%

    No Known Activations