© 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. 76583
    Prev
    Next
    INDEX
    Explanations

    programming imports

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

    The neuron strongly activates on lines that import external libraries or modules (i.e. “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
     only
    -1.60
     by
    -1.55
     because
    -1.44
     now
    -1.42
     these
    -1.41
     for
    -1.41
     more
    -1.40
     people
    -1.40
     Since
    -1.38
     Only
    -1.38
    POSITIVE LOGITS
    ↵
    1.70
    ↵↵↵
    1.48
    ↵↵
    1.30
     faciliter
    1.27
    ↵↵↵↵↵↵↵↵↵↵
    1.25
     EVEN
    1.23
    ↵↵↵↵↵↵↵↵↵↵↵
    1.21
     diverses
    1.18
    NEVER
    1.17
     många
    1.16
    Activations Density 0.017%

    No Known Activations