© 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. 22-GEMMASCOPE-RES-131K
    7. 98309
    Prev
    Next
    INDEX
    Explanations

    code-related examples

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

    The neuron strongly activates on single-letter labels in parentheses (e.g. “(a)”, “(b)”, “(c)”) used to mark list or answer‐choice items.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    苅
    -1.05
    槙
    -0.98
    鎳
    -0.98
    entière
    -0.97
     inspirasi
    -0.97
    refund
    -0.96
    noted
    -0.96
    famous
    -0.96
    izator
    -0.96
    lihood
    -0.95
    POSITIVE LOGITS
     then
    1.02
     never
    0.98
     how
    0.95
    ền
    0.95
    未知
    0.93
     correctly
    0.89
     appears
    0.89
     Çünkü
    0.88
    年には
    0.88
     μὲν
    0.85
    Activations Density 0.001%

    No Known Activations