© 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. 130741
    Prev
    Next
    INDEX
    Explanations

    The main thing this neuron does is detect commas (i.e. comma separators) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    comma separated text

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    नलोड
    -2.14
     Belakang
    -2.00
     Should
    -1.98
    should
    -1.91
    大多数
    -1.88
     contactar
    -1.81
    也
    -1.76
     Informasi
    -1.64
     hone
    -1.64
    amerikan
    -1.64
    POSITIVE LOGITS
    饜
    2.23
    änemark
    1.88
     solução
    1.87
    }\
    1.82
    }{
    1.76
     definição
    1.75
    强行
    1.74
    笵
    1.74
    ${\
    1.73
    ().__
    1.73
    Activations Density 0.011%

    No Known Activations