© 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. 64057
    Prev
    Next
    INDEX
    Explanations

    code structure keywords

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

    The neuron primarily activates on numeric literal tokens (sequences of digits) in the 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
    至此
    -1.07
     音乐
    -0.97
    int
    -0.90
    ಎ
    -0.86
    很多的
    -0.85
    printf
    -0.85
     vienas
    -0.84
    cout
    -0.84
    回憶
    -0.84
    ៊
    -0.83
    POSITIVE LOGITS
     let
    1.39
     if
    1.38
    let
    1.24
     если
    1.01
     {
    1.01
     когда
    0.98
     when
    0.96
    ({
    0.93
    (['
    0.93
    лет
    0.91
    Activations Density 0.014%

    No Known Activations