© 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. 103648
    Prev
    Next
    INDEX
    Explanations

    reversed words, backronyms, or specific terms

    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
    的同时
    0.41
    နယ်
    0.37
     പിന്നീ
    0.37
    してきた
    0.36
    verture
    0.36
     ناج
    0.35
    iec
    0.35
    anju
    0.35
    <unused2173>
    0.35
    UniqueID
    0.35
    POSITIVE LOGITS
     converted
    1.24
     transformed
    1.24
     translated
    1.16
    converted
    1.11
    transformed
    1.10
     resized
    1.04
    Converted
    1.02
    translated
    1.01
     transposed
    1.01
     minus
    0.94
    Activations Density 0.001%

    No Known Activations