© 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. 12976
    Prev
    Next
    INDEX
    Explanations

    waterfalls and delete clauses

    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
    啃
    0.41
     অভিযুক্ত
    0.39
    pts
    0.39
    🦂
    0.39
     зло
    0.38
     पॉली
    0.38
     graveyard
    0.38
     phenomen
    0.37
     clay
    0.37
     قبر
    0.37
    POSITIVE LOGITS
     waterfall
    1.61
     waterfalls
    1.54
     cascades
    1.52
     cascade
    1.48
    Waterfall
    1.43
     cascading
    1.42
     Waterfall
    1.40
    Cascade
    1.34
    瀑
    1.34
    cascade
    1.30
    Activations Density 0.011%

    No Known Activations