© 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. 35985
    Prev
    Next
    INDEX
    Explanations

    contrast introducing a continuation

    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
     while
    -1.63
     although
    -1.52
     aunque
    -1.47
     даже
    -1.45
     even
    -1.41
     навіть
    -1.34
     vaikka
    -1.27
     bahkan
    -1.21
     ولكن
    -1.21
     though
    -1.16
    POSITIVE LOGITS
     nevertheless
    2.00
     it
    1.73
     nonetheless
    1.70
     still
    1.57
     tetap
    1.55
    还是要
    1.39
     vẫn
    1.34
     remains
    1.28
    etheless
    1.24
    还是
    1.22
    Activations Density 0.085%

    No Known Activations