© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 105719
    Prev
    Next
    INDEX
    Explanations

    programming code inclusions

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

    The neuron detects the opening quotation marks that introduce file path strings in include or import statements.

    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
     how
    -1.77
     at
    -1.71
     each
    -1.61
     why
    -1.60
     out
    -1.60
    何况
    -1.57
     nahezu
    -1.54
     with
    -1.48
     through
    -1.45
    為何
    -1.45
    POSITIVE LOGITS
    included
    1.86
     peluche
    1.73
    
    1.66
     Perſ
    1.59
     Meksiko
    1.53
     Objek
    1.50
    鹩
    1.46
    tung
    1.45
    睃
    1.45
    brief
    1.44
    Activations Density 0.017%

    No Known Activations