© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47586
    Prev
    Next
    INDEX
    Explanations

    import statements for Python libraries

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

    This neuron detects Python import statements and related module‐ or package‐name tokens.

    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
     strip
    -0.79
    pascal
    -0.75
    bilan
    -0.75
    WithType
    -0.74
     Crowe
    -0.73
     практики
    -0.73
    üyada
    -0.73
    补
    -0.73
     أب
    -0.73
    🕰
    -0.73
    POSITIVE LOGITS
     matplotlib
    1.43
    matplotlib
    1.05
     warnings
    0.84
     MAT
    0.83
     Мат
    0.77
    ANCES
    0.75
    guerite
    0.75
     مات
    0.75
     Pact
    0.74
     panini
    0.74
    Activations Density 0.011%

    No Known Activations