© 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. 53-GEMMASCOPE-2-RES-262K
    7. 40861
    Prev
    Next
    INDEX
    Explanations

    carrying heavy things

    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_53_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     possessions
    0.46
     cufflinks
    0.46
    蒐
    0.43
    小題
    0.41
     identifiers
    0.41
     Disposable
    0.41
     belongings
    0.40
    Shoes
    0.39
     laisser
    0.39
    捨て
    0.38
    POSITIVE LOGITS
     heavy
    1.21
    heavy
    1.11
     тяже
    1.09
    Heavy
    1.04
    重
    1.00
     тяжё
    0.97
     Heavy
    0.96
     cięż
    0.95
     heavier
    0.94
     schweren
    0.92
    Activations Density 0.013%

    No Known Activations