© 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. 82896
    Prev
    Next
    INDEX
    Explanations

    code syntax and properties

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

    The neuron fires on programming‐style tokens—variable names, numeric literals, code punctuation, and comment markers—i.e. snippets of source 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
    userList
    -0.84
    بیشتر
    -0.84
    ständig
    -0.84
     ファミ
    -0.82
     :)</
    -0.82
    Watcher
    -0.82
     Eğer
    -0.81
    มือ
    -0.80
     Condé
    -0.80
    بدون
    -0.79
    POSITIVE LOGITS
     Florida
    1.02
    と思い
    0.82
     Kategorie
    0.79
     oração
    0.77
     Ziele
    0.77
     ожи
    0.75
     região
    0.74
     aliran
    0.72
     группе
    0.70
    flé
    0.69
    Activations Density 0.001%

    No Known Activations