© 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. 73790
    Prev
    Next
    INDEX
    Explanations

    but followed by qualifier

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

    The neuron strongly activates on the conjunction “but,” signaling contrastive clauses.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     Lite
    -0.91
    minimal
    -0.91
    很少
    -0.89
    เล็ก
    -0.89
     minimal
    -0.88
     seksual
    -0.87
    elezo
    -0.85
     minimalist
    -0.85
    Minimal
    -0.85
    شود
    -0.84
    POSITIVE LOGITS
     zato
    0.90
     suffice
    0.80
     porém
    0.80
    lakukan
    0.80
     immerhin
    0.79
     larger
    0.78
    升
    0.78
     wider
    0.78
     upgraded
    0.78
     intensive
    0.77
    Activations Density 0.083%

    No Known Activations