© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-65K
    7. 1672
    Prev
    Next
    INDEX
    Explanations

    contrasting conjunctions like 'but'

    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_16_width_65k_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
    for
    0.47
    Y
    0.47
    Bridge
    0.42
    4
    0.42
     for
    0.40
    ’
    0.39
    four
    0.39
    X
    0.39
    B
    0.38
    ف
    0.38
    POSITIVE LOGITS
     אבל
    0.42
     কিন্ত
    0.39
    と思いますが
    0.39
     եւ
    0.39
     lakini
    0.38
    ກັບ
    0.38
    けれど
    0.38
     ஆனால்
    0.38
     എന്നാൽ
    0.38
     ਅਤੇ
    0.38
    Activations Density 0.740%

    No Known Activations