© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113431
    Prev
    Next
    INDEX
    Explanations

    arabic names and words

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

    The neuron flags tokens written in Arabic‐script characters (e.g. Arabic, Persian, Urdu).

    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
     our
    -1.88
     a
    -1.77
    p
    -1.56
    ",
    -1.50
    /
    -1.49
    0
    -1.46
    You
    -1.43
     раст
    -1.38
    裡的
    -1.38
     the
    -1.35
    POSITIVE LOGITS
    welli
    1.68
    栊
    1.66
    
    1.66
     сумка
    1.64
    髅
    1.64
    vestres
    1.63
    
    1.60
    aturi
    1.57
     هناك
    1.56
    רושלים
    1.53
    Activations Density 0.005%

    No Known Activations