© 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. 34-GEMMASCOPE-RES-131K
    4. 4376
    Prev
    Next
    INDEX
    Explanations

    import com

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

    The neuron activates almost exclusively on the keyword “import,” effectively detecting import statements in 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_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
     then
    -1.59
     now
    -1.36
    Then
    -1.30
    then
    -1.17
     chrétienne
    -1.16
     by
    -1.13
    Now
    -1.13
    Still
    -1.12
    
    -1.10
     being
    -1.09
    POSITIVE LOGITS
     com
    1.57
     with
    1.05
    com
    1.00
     could
    0.99
     здесь
    0.98
     come
    0.97
     Com
    0.97
    mathrm
    0.91
     couldn
    0.91
     the
    0.90
    Activations Density 0.005%

    No Known Activations