© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11484
    Prev
    Next
    INDEX
    Explanations

    whereas and contrastive conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    прочем
    0.41
    )>
    0.39
     ጊዜ
    0.39
    ιδ
    0.37
     ግን
    0.37
     কিন্তু
    0.36
    >*
    0.36
    Without
    0.36
    ífico
    0.36
    >
    0.35
    POSITIVE LOGITS
     whereas
    1.63
     sedangkan
    1.48
    whereas
    1.48
     tandis
    1.36
     Sedangkan
    1.31
     Whereas
    1.30
    Whereas
    1.21
    而
    1.16
     بينما
    1.09
     mentre
    1.07
    Activations Density 0.261%

    No Known Activations