© 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. 8649
    Prev
    Next
    INDEX
    Explanations

    urls and foreign words

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

    The neuron detects spans of Arabic script text (Arabic words).

    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
     a
    -2.05
     the
    -1.95
     eminent
    -1.93
     بهترین
    -1.88
    ↵
    -1.82
    大好きです
    -1.77
     ''
    -1.76
    ACIONES
    -1.72
     één
    -1.70
    螣
    -1.67
    POSITIVE LOGITS
     Dingen
    2.53
     Both
    2.50
    The
    2.42
     aforementioned
    2.20
     sportiva
    2.17
     Neither
    2.16
     Saltar
    2.11
     borgo
    2.05
     этом
    1.99
     Ultimately
    1.99
    Activations Density 0.001%

    No Known Activations