© 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. 98191
    Prev
    Next
    INDEX
    Explanations

    but, although, nevertheless

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

    This neuron detects contrastive conjunctions—especially the word “but” signaling a shift or exception.

    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
    Warrior
    -0.96
    gaven
    -0.93
    izando
    -0.90
     nėra
    -0.87
     canlynol
    -0.84
    Šalt
    -0.82
     насеља
    -0.82
    yaitu
    -0.82
     dė
    -0.82
     précisément
    -0.82
    POSITIVE LOGITS
     nonetheless
    1.13
     exist
    1.09
     nevertheless
    1.05
     exists
    1.02
     secretly
    1.01
     existence
    1.01
     importance
    0.97
    Nonetheless
    0.97
    Once
    0.93
     behind
    0.92
    Activations Density 0.080%

    No Known Activations