© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111698
    Prev
    Next
    INDEX
    Explanations

    Moroccan and Morocco

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

    The neuron selectively activates on proper nouns and place names relating to Morocco (e.g., “Moroccan,” “Morocco,” “Western Sahara”).

    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
     florales
    -1.21
    Now
    -1.17
     лучше
    -1.05
     chanteuse
    -1.02
    周泽
    -1.02
    ⤒
    -0.99
    愜
    -0.95
    Then
    -0.94
    ◆◆
    -0.94
     уже
    -0.93
    POSITIVE LOGITS
     limitado
    1.12
     IActionResult
    1.10
    verick
    1.10
     deportiva
    1.08
     Morocco
    1.07
    ActionResult
    1.03
    hésite
    1.02
    ℒ
    1.02
    randa
    1.02
    hibli
    1.01
    Activations Density 0.049%

    No Known Activations