© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 67970
    Prev
    Next
    INDEX
    Explanations

    contrasting conjunctions

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

    The neuron flags contrastive or adversative transition points—particularly sentence-initial connectors like “but,” “however,” “but the…,” “but when,” “but what,” etc.

    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
    雖然
    -1.25
     quindi
    -1.24
     therefore
    -1.22
    虽然
    -1.06
    therefore
    -1.04
    雖
    -1.04
     and
    -1.02
     thus
    -0.96
     hence
    -0.96
    евна
    -0.95
    POSITIVE LOGITS
     nevertheless
    1.94
     nonetheless
    1.84
     still
    1.69
     vẫn
    1.45
     dennoch
    1.45
     kuitenkin
    1.38
     it
    1.27
    仍
    1.27
     trotzdem
    1.27
    Nevertheless
    1.24
    Activations Density 0.016%

    No Known Activations