© 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. 76537
    Prev
    Next
    INDEX
    Explanations

    codes and designations

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

    The neuron is detecting punctuation marks and separators—especially commas and parentheses.

    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
     firearm
    -0.96
     rifle
    -0.96
     guns
    -0.94
     rifles
    -0.93
     gun
    -0.89
     firearms
    -0.88
    🔫
    -0.85
    盔
    -0.85
     Simpson
    -0.83
    枪
    -0.83
    POSITIVE LOGITS
    merate
    0.88
    Constructors
    0.87
    classname
    0.86
     default
    0.83
     entanto
    0.82
     unlocks
    0.80
     улуч
    0.79
    steamcommunity
    0.77
     Kuznets
    0.77
    remacy
    0.77
    Activations Density 0.009%

    No Known Activations