© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2850
    Prev
    Next
    INDEX
    Explanations

    R code syntax and assignment

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

    This neuron flags numeric literal tokens (i.e. numbers) in R 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
     or
    -0.83
     an
    -0.77
    careers
    -0.77
    wnd
    -0.75
     Transport
    -0.75
     while
    -0.73
    UIImageView
    -0.71
     Heilig
    -0.71
     that
    -0.70
    itag
    -0.70
    POSITIVE LOGITS
    TRUE
    1.47
    [,
    1.27
     %>%
    1.26
    FALSE
    1.23
     FALSE
    1.08
     TRUE
    1.06
    paste
    1.05
    ggplot
    1.04
     <-
    1.02
     paste
    0.99
    Activations Density 0.090%

    No Known Activations