© 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. 81385
    Prev
    Next
    INDEX
    Explanations

    Python @property decorator

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

    This neuron activates on long runs of whitespace (indentation) 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
    ைக்
    -0.79
    lani
    -0.79
     큰
    -0.76
    现金
    -0.74
    houding
    -0.72
     allem
    -0.72
     darin
    -0.71
    ּוֹ
    -0.71
    ័
    -0.70
    satunya
    -0.69
    POSITIVE LOGITS
     property
    1.28
    property
    1.21
     يد
    0.81
    COV
    0.79
    報酬
    0.77
     bays
    0.77
     properties
    0.77
     Prid
    0.77
     Property
    0.77
    Property
    0.76
    Activations Density 0.003%

    No Known Activations