© 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. 102939
    Prev
    Next
    INDEX
    Explanations

    accessing object properties or methods

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

    This neuron activates on programming identifiers (variable, function, or property names) 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
     which
    -1.00
     οπο
    -0.98
     aislados
    -0.96
    されない
    -0.96
     who
    -0.90
     always
    -0.88
    しなかった
    -0.87
     cuyas
    -0.87
     that
    -0.86
    出来ない
    -0.86
    POSITIVE LOGITS
    ['
    1.05
     ContentValues
    1.01
     JAXBElement
    0.98
    athyroid
    0.98
    ⓐ
    0.97
     createSprite
    0.96
    глед
    0.94
     TextAlign
    0.94
    tragung
    0.93
    ._
    0.91
    Activations Density 0.018%

    No Known Activations