© 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. 73776
    Prev
    Next
    INDEX
    Explanations

    import processing

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

    The neuron fires strongly on fully qualified package or import path tokens (e.g. Java “package …” and “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_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
    Frequ
    -0.91
    이며
    -0.78
    glected
    -0.76
    frequ
    -0.75
     identific
    -0.74
    ioren
    -0.72
    Predicted
    -0.70
    tigheter
    -0.69
    PRACT
    -0.69
    apikey
    -0.69
    POSITIVE LOGITS
     Processing
    1.38
    sketch
    1.23
     sketch
    1.23
     Sketch
    1.13
     sketches
    1.13
    processing
    1.12
    Processing
    1.11
     processing
    1.01
    println
    1.00
     PROCESSING
    0.99
    Activations Density 0.049%

    No Known Activations