© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128529
    Prev
    Next
    INDEX
    Explanations

    conjunctions of contrast

    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_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
    fortunately
    -1.04
    Fortunately
    -1.02
     fortunately
    -1.01
     thankfully
    -1.00
     Fortunately
    -0.98
     heure
    -0.96
     innan
    -0.93
     hopefully
    -0.86
     luckily
    -0.85
     bande
    -0.84
    POSITIVE LOGITS
     nevertheless
    1.25
     dennoch
    1.24
     nonetheless
    1.16
     trotzdem
    1.10
    やはり
    1.02
     Allerdings
    1.02
     still
    0.90
     Nevertheless
    0.88
    时间
    0.84
     allerdings
    0.84
    Activations Density 0.071%

    No Known Activations