© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 631
    Prev
    Next
    INDEX
    Explanations

    hours and am/pm indicators

    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_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     تث
    0.29
    Employer
    0.29
    ourcen
    0.28
     intelligible
    0.28
     unint
    0.28
     generalizes
    0.27
     encom
    0.27
    Minute
    0.27
     fuzz
    0.27
     <=
    0.26
    POSITIVE LOGITS
    pm
    0.77
     pm
    0.70
     noon
    0.63
     PM
    0.60
    noon
    0.56
    PM
    0.55
     बजे
    0.55
    午後
    0.53
     afternoon
    0.50
    下午
    0.49
    Activations Density 0.019%

    No Known Activations