© 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. 40979
    Prev
    Next
    INDEX
    Explanations

    multilingual tokens

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

    This neuron fires on rare or foreign (nonstandard/low‐frequency) tokens.

    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
     of
    -2.17
    ’
    -2.08
     that
    -1.77
    1
    -1.72
    那我
    -1.72
    X
    -1.69
    3
    -1.68
    2
    -1.66
    、“
    -1.66
     can
    -1.65
    POSITIVE LOGITS
     僕
    1.84
    蛩
    1.73
     akumulator
    1.70
     छोड़
    1.70
    dámské
    1.68
     スクリーン
    1.68
     necesar
    1.68
    archiwizowane
    1.66
     内衣
    1.64
     fometimes
    1.60
    Activations Density 0.002%

    No Known Activations