© 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. 119254
    Prev
    Next
    INDEX
    Explanations

    code import paths

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

    The neuron detects lines that import modules or classes, specifically the imported identifier in import/from-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
     During
    -1.57
     any
    -1.48
     if
    -1.48
    During
    -1.48
    Despite
    -1.40
    Since
    -1.36
     because
    -1.35
     on
    -1.29
     for
    -1.27
     one
    -1.27
    POSITIVE LOGITS
     nieuwe
    1.22
     vérifier
    1.15
     praktische
    1.13
     aceste
    1.13
     périodes
    1.11
     flera
    1.09
     также
    1.09
     goofy
    1.09
    オリーブ
    1.09
     gouttes
    1.08
    Activations Density 0.021%

    No Known Activations