© 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. 22-GEMMASCOPE-RES-131K
    7. 68440
    Prev
    Next
    INDEX
    Explanations

    import statements in code

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

    The neuron is tuned to detect numeric tokens (digits and numbers) 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_22/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
    AJAS
    -1.02
    mäh
    -0.99
     beide
    -0.96
     hukuman
    -0.93
    tividade
    -0.93
    (￣
    -0.91
    umers
    -0.91
     pernikahan
    -0.91
    panes
    -0.90
    Тарих
    -0.89
    POSITIVE LOGITS
     Ihnen
    0.94
    で見る
    0.94
    why
    0.93
    важа
    0.92
    同じ
    0.90
     impresionantes
    0.89
     acht
    0.88
     ameryka
    0.88
     why
    0.87
     девя
    0.87
    Activations Density 0.002%

    No Known Activations