© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 102708
    Prev
    Next
    INDEX
    Explanations

    java code annotations and declarations

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

    The neuron fires on numeric literal tokens (digit sequences) in code, especially numbers used as annotation parameter values.

    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
    ərb
    -0.93
    ];
    -0.93
     disponibile
    -0.84
     informée
    -0.84
     Hentet
    -0.83
    рева
    -0.82
    ();
    -0.79
     особенно
    -0.78
    retanto
    -0.76
    文化
    -0.76
    POSITIVE LOGITS
     {
    1.37
     {"
    1.28
     {'
    1.22
    ={
    1.18
    ({
    1.16
     ={
    1.14
     {
    
    1.07
    ,{
    1.04
    +{
    1.03
     {})
    0.88
    Activations Density 0.008%

    No Known Activations