© 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. 34-GEMMASCOPE-RES-131K
    7. 77619
    Prev
    Next
    INDEX
    Explanations

    R code for mutate and geom

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

    The neuron is picking up on R dplyr pipeline code (e.g. the “%>%” operator and related verbs like filter, group_by, mutate).

    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
     Rial
    -0.84
    nost
    -0.81
     paździer
    -0.78
    inx
    -0.77
    𝘙
    -0.77
     turret
    -0.76
     opt
    -0.76
     Казах
    -0.74
     sack
    -0.73
     móg
    -0.71
    POSITIVE LOGITS
     aesthetics
    1.14
     aesthetic
    1.06
     geom
    0.95
    geom
    0.94
    mutate
    0.94
     Aesthetics
    0.93
     %>%
    0.91
     Aesthetic
    0.90
     estética
    0.84
    ACS
    0.81
    Activations Density 0.071%

    No Known Activations