© 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. 98039
    Prev
    Next
    INDEX
    Explanations

    free of charge

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

    The neuron is strongly activated by commas (especially in license/permission statements), i.e. it detects the comma punctuation.

    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
     rings
    -0.81
     whether
    -0.80
     bags
    -0.78
    lid
    -0.73
     writers
    -0.72
     no
    -0.71
     authors
    -0.70
    走
    -0.70
     Mauro
    -0.69
     is
    -0.68
    POSITIVE LOGITS
     бюдже
    0.81
     Fait
    0.80
    Tos
    0.77
     $\|
    0.75
     politie
    0.72
    umuz
    0.71
    initializer
    0.70
    worden
    0.69
    nuit
    0.69
    Rha
    0.69
    Activations Density 0.044%

    No Known Activations