© 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. 219920
    Prev
    Next
    INDEX
    Explanations

    dusting and dripping

    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
    踮
    0.41
     ప్రే
    0.41
     intensifying
    0.41
     nearing
    0.40
     slams
    0.40
     бал
    0.40
     hoping
    0.39
    匙
    0.39
     berdoa
    0.38
    希望能
    0.38
    POSITIVE LOGITS
     undamaged
    0.63
     shaken
    0.60
     dusted
    0.58
     dust
    0.58
     cleanup
    0.56
     recuperación
    0.56
     recover
    0.55
     recovery
    0.55
     recovers
    0.55
     dusting
    0.55
    Activations Density 0.015%

    No Known Activations