© 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. 41-GEMMASCOPE-2-RES-262K
    7. 26750
    Prev
    Next
    INDEX
    Explanations

    years and technology models

    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_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    🥲
    0.92
     pandemic
    0.91
     covid
    0.87
     COVID
    0.86
    COVID
    0.85
     कोविड
    0.84
     코로나
    0.84
    🤍
    0.83
     pandemi
    0.82
     Covid
    0.81
    POSITIVE LOGITS
     ২০১৮
    1.16
     ২০১৯
    0.71
    🖒
    0.55
     ২০১৭
    0.53
     Trump
    0.48
    RichEmbed
    0.48
     २०
    0.47
     Brexit
    0.47
    Trump
    0.46
    Brexit
    0.46
    Activations Density 0.006%

    No Known Activations