© 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. 81539
    Prev
    Next
    INDEX
    Explanations

    with or without

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

    The neuron strongly activates on the conjunction “and” (and similar linking words like “or,” “with,” “without”) as they occur in software license or copyright 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
     arro
    -0.88
     raya
    -0.86
     Transporte
    -0.83
    {})
    -0.82
    里
    -0.81
    ysteme
    -0.80
    Logging
    -0.78
     apto
    -0.78
     conta
    -0.77
     gjennom
    -0.77
    POSITIVE LOGITS
     anzub
    0.84
     estarán
    0.80
    IMDB
    0.80
     llevaron
    0.79
     ايران
    0.79
     സ്
    0.78
     diritto
    0.78
    lcccc
    0.78
    eces
    0.78
    imagin
    0.77
    Activations Density 0.006%

    No Known Activations