© 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. 10-GEMMASCOPE-RES-131K
    7. 119070
    Prev
    Next
    INDEX
    Explanations

    sequence context following punctuation

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

    This neuron detects commas (the comma punctuation token) in text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     minera
    -2.31
     ſta
    -2.20
     industrie
    -2.13
     Israël
    -2.05
     protéger
    -2.00
    蕷
    -2.00
     itali
    -1.99
    麃
    -1.99
    鉨
    -1.99
     henne
    -1.97
    POSITIVE LOGITS
     is
    3.23
     should
    2.44
     by
    2.36
     before
    2.33
     to
    2.33
     two
    2.28
     they
    2.23
     and
    2.17
     has
    2.11
     A
    2.08
    Activations Density 0.010%

    No Known Activations