© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 53576
    Prev
    Next
    INDEX
    Explanations

    contrast conjunction

    np_acts-logits-general · gemini-2.5-flash-lite

    but introduces contrast

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     however
    0.66
     HOWEVER
    0.59
     However
    0.57
    however
    0.56
    However
    0.54
     Despite
    0.52
     다만
    0.51
    却
    0.48
     Notwithstanding
    0.48
     jedoch
    0.48
    POSITIVE LOGITS
    总体
    0.65
    基本的に
    0.64
    否则
    0.63
    整体
    0.62
     certamente
    0.61
    一般来说
    0.60
     sicuramente
    0.60
    整體
    0.59
    sonsten
    0.59
     overall
    0.58
    Activations Density 0.078%

    No Known Activations