© 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. 34-GEMMASCOPE-RES-131K
    7. 103527
    Prev
    Next
    INDEX
    Explanations

    xml and file paths

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

    The neuron is detecting file‐related tokens—especially file extensions and I/O operations (e.g. “xml,” “open,” “stream”).

    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
    ={
    -0.89
     justice
    -0.83
     ү
    -0.80
    warna
    -0.80
    chak
    -0.76
    fandom
    -0.76
     bodyParser
    -0.76
    titus
    -0.75
    /***
    -0.75
    bucks
    -0.73
    POSITIVE LOGITS
    Kamera
    1.27
    Katalog
    1.11
    ﹫
    1.05
    Specifik
    1.02
    Recept
    1.00
    Spann
    0.98
    ↵
    0.98
    again
    0.98
    gaven
    0.97
    Länge
    0.96
    Activations Density 0.000%

    No Known Activations