© 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. 83832
    Prev
    Next
    INDEX
    Explanations

    contrast and concessionary conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     également
    -2.16
     также
    -2.11
    だけでなく
    -2.00
     también
    -1.95
     również
    -1.92
     nawet
    -1.91
     even
    -1.90
     incluso
    -1.89
     também
    -1.88
     også
    -1.85
    POSITIVE LOGITS
     nevertheless
    2.64
     nonetheless
    2.53
     dennoch
    2.22
     immerhin
    2.08
    Nevertheless
    2.06
     trotzdem
    2.06
     зато
    2.05
     comunque
    1.86
    Nonetheless
    1.80
     Nevertheless
    1.80
    Activations Density 0.124%

    No Known Activations