© 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
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 5523
    Prev
    Next
    INDEX
    Explanations

    column identifier

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

    The neuron strongly activates on programming‐style identifiers—especially R function names and argument or parameter names—marking code tokens in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    αιρε
    0.63
    -'+
    0.63
    Require
    0.63
     webpack
    0.56
     przec
    0.56
    гно
    0.55
     memerlukan
    0.55
     sicherlich
    0.55
    __).
    0.55
     require
    0.54
    POSITIVE LOGITS
    $
    0.86
     %>%
    0.80
    $
    0.79
    [[
    0.75
    unlist
    0.73
    ))%>%
    0.73
     ..$
    0.72
    $`
    0.71
    [,
    0.69
     [,
    0.68
    Activations Density 0.027%

    No Known Activations