© 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. 10-GEMMASCOPE-RES-131K
    7. 119568
    Prev
    Next
    INDEX
    Explanations

    contrasting discourse markers

    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_10/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
     hemd
    -1.87
     koel
    -1.78
     poches
    -1.67
     zui
    -1.66
    烀
    -1.65
     côtés
    -1.63
    AGAIN
    -1.61
     gouttes
    -1.56
     geel
    -1.54
     trous
    -1.53
    POSITIVE LOGITS
     Although
    2.28
    Although
    2.11
     Though
    2.11
     Despite
    2.08
    Though
    2.03
     However
    1.88
    While
    1.82
    Despite
    1.76
     Following
    1.73
     so
    1.72
    Activations Density 0.058%

    No Known Activations