© 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. 31-GEMMASCOPE-2-RES-65K
    7. 44629
    Prev
    Next
    INDEX
    Explanations

    mouthful of, balances a, curled back

    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_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ﻟ
    0.42
     zmian
    0.41
     ограни
    0.40
     Hồng
    0.40
     últ
    0.39
     этих
    0.39
    停车
    0.39
     ສຳ
    0.39
    찬
    0.39
     ал
    0.39
    POSITIVE LOGITS
     atau
    0.45
    .!
    0.44
     eller
    0.43
    ologist
    0.42
     alebo
    0.41
    .*
    0.41
     Preferably
    0.41
     preferably
    0.41
    または
    0.40
    ism
    0.40
    Activations Density 0.009%

    No Known Activations