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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 75260
    Prev
    Next
    INDEX
    Explanations

    `using System.Threading.Tasks`

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

    The neuron is detecting numeric literals (especially decimal numbers) in the code.

    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
     his
    -1.91
     "
    -1.72
     \
    -1.69
     новой
    -1.68
     its
    -1.68
    ,"
    -1.67
    .'
    -1.66
    訁
    -1.63
    ..........
    -1.63
    \_
    -1.63
    POSITIVE LOGITS
     pistolet
    1.47
     torba
    1.47
     薯
    1.43
    zzazione
    1.41
     porcent
    1.41
     Preferencias
    1.40
    
    1.40
     gereken
    1.40
     Presidente
    1.37
     постепенно
    1.37
    Activations Density 0.005%

    No Known Activations