© 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. 65645
    Prev
    Next
    INDEX
    Explanations

    code blocks and function calls

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

    This neuron activates on programming-language tokens—especially JavaScript/TypeScript code syntax (imports, keywords like class, function names, braces, parentheses, etc.).

    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
     basis
    -1.02
    uppo
    -0.96
    xel
    -0.83
    Basis
    -0.79
    Życiorys
    -0.79
     podstaw
    -0.77
    pios
    -0.73
     apoy
    -0.73
     support
    -0.72
    อี
    -0.71
    POSITIVE LOGITS
    ({
    2.27
     ({
    2.14
    (({
    2.02
    ({
    1.60
     {
    1.41
    >({
    1.31
    ,{
    1.30
    ",{
    1.30
    ={({
    1.25
     $\{
    1.23
    Activations Density 0.011%

    No Known Activations