© 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. 83856
    Prev
    Next
    INDEX
    Explanations

    opening files or database connections

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

    This neuron lights up on code tokens that perform file or model I/O operations (e.g. open, save, load, connect).

    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
     that
    -1.02
    umbo
    -0.85
     itself
    -0.82
    ierzch
    -0.75
     nobody
    -0.75
     initially
    -0.75
     such
    -0.73
    dihydro
    -0.72
     uzyskać
    -0.71
    _
    -0.71
    POSITIVE LOGITS
     "./
    1.78
     "../
    1.42
     './
    1.39
     "
    1.36
     “
    1.30
    ="./
    1.23
    ("./
    1.23
     '../
    1.22
    ./
    1.20
    ('./
    1.15
    Activations Density 0.037%

    No Known Activations