© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70141
    Prev
    Next
    INDEX
    Explanations

    Ruby `do` blocks

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

    This neuron detects Ruby’s block-opening “do” keyword (especially in RSpec/test declarations).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    鸰
    -2.05
    -“
    -1.99
     (“
    -1.87
    鱟
    -1.77
    ’,
    -1.75
    辚
    -1.75
     correctes
    -1.74
     (‘
    -1.71
    鯷
    -1.70
    流畅
    -1.68
    POSITIVE LOGITS
     However
    2.38
     但
    2.13
    ৄ
    2.06
     giapponese
    1.97
     reign
    1.96
    ormány
    1.92
     These
    1.87
    0
    1.81
    。
    1.80
     IBRARY
    1.79
    Activations Density 0.006%

    No Known Activations