© 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. 16-GEMMASCOPE-2-RES-262K
    7. 145443
    Prev
    Next
    INDEX
    Explanations

    It is `that`

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     as
    0.68
    ون
    0.66
    ها
    0.65
    자
    0.62
    اته
    0.62
     about
    0.61
    ан
    0.60
    తో
    0.59
    ↵
    0.59
     doesn
    0.59
    POSITIVE LOGITS
    í
    0.65
    锌
    0.61
     प्रस्ताव
    0.61
    0.59
    ú
    0.59
    ess
    0.58
     पीएम
    0.58
     kertas
    0.58
     giust
    0.57
     केंद्र
    0.57
    Activations Density 0.010%

    No Known Activations