© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 4792
    Prev
    Next
    INDEX
    Explanations

    temporal markers like before and after

    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
     xer
    0.38
     fik
    0.37
     Tabelle
    0.36
     eventualmente
    0.35
    素
    0.35
    部品
    0.35
    غاية
    0.35
     素
    0.35
    名
    0.35
     contenus
    0.34
    POSITIVE LOGITS
     before
    0.85
     whenever
    0.81
     BEFORE
    0.80
     перед
    0.74
     sebelum
    0.72
     قبل
    0.71
     أثناء
    0.71
    before
    0.70
    ก่อน
    0.68
     podczas
    0.68
    Activations Density 0.316%

    No Known Activations