© 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. 103407
    Prev
    Next
    INDEX
    Explanations

    comma software

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

    The neuron strongly responds to comma characters, especially those in legal/license boilerplate.

    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
    ínű
    -0.83
     Maradona
    -0.74
    affected
    -0.73
    綫
    -0.71
    ected
    -0.71
     soffer
    -0.71
    éry
    -0.71
    ीय
    -0.69
    ɠ
    -0.69
     WTA
    -0.68
    POSITIVE LOGITS
    dekat
    0.68
    agulation
    0.67
    Shu
    0.67
     viviendas
    0.67
    рат
    0.65
    ्
    0.64
     馆
    0.64
    子ども
    0.64
     loader
    0.64
    IVER
    0.63
    Activations Density 0.042%

    No Known Activations