© 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. 67889
    Prev
    Next
    INDEX
    Explanations

    contrast or concession 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_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
    also
    -1.13
     например
    -1.06
    especially
    -1.02
    Then
    -1.02
     include
    -1.01
     arşivlendi
    -0.99
     aproximativ
    -0.98
    ઃ
    -0.98
    corns
    -0.97
     misalnya
    -0.96
    POSITIVE LOGITS
     although
    1.66
     but
    1.65
    Aunque
    1.45
     aunque
    1.45
     it
    1.30
     though
    1.24
     that
    1.23
     όμως
    1.23
    Đây
    1.20
    ないけど
    1.16
    Activations Density 0.028%

    No Known Activations