© 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. 34-GEMMASCOPE-RES-131K
    7. 64605
    Prev
    Next
    INDEX
    Explanations

    Arabic names and words starting with J

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

    The neuron fires strongly on named entities—especially Arabic‐script or transliterated proper names of people, places, and organizations.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    طلحات
    -0.76
     पढ़
    -0.72
     dib
    -0.71
     nage
    -0.71
     llorando
    -0.69
     RATES
    -0.69
    Pools
    -0.69
    BadRequest
    -0.69
     Deals
    -0.68
    banding
    -0.68
    POSITIVE LOGITS
     raccol
    0.83
     Attra
    0.83
    搜索
    0.77
    Soc
    0.74
     quack
    0.73
     समु
    0.73
    こともあり
    0.71
    ثم
    0.71
     quality
    0.70
     esfor
    0.69
    Activations Density 0.011%

    No Known Activations