© 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. 412
    Prev
    Next
    INDEX
    Explanations

    code punctuation

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

    The neuron fires on the individual items in array or list literals (i.e. values inside [ ] in JSON/JS/Python 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
    城的
    -0.87
     نقاشی
    -0.87
    档案馆
    -0.85
     algum
    -0.85
     mantend
    -0.84
    因为它
    -0.82
    čenje
    -0.82
     मूल
    -0.82
    низ
    -0.81
    gnac
    -0.79
    POSITIVE LOGITS
    ,,,,
    1.07
    ,,,
    1.00
     about
    1.00
     such
    0.90
    {
    0.90
    createElement
    0.86
    ..........
    0.86
    ...............
    0.84
     hecta
    0.84
    这么
    0.84
    Activations Density 0.029%

    No Known Activations