© 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-262K
    7. 21678
    Prev
    Next
    INDEX
    Explanations

    volunteer, pilot, evaluation, struggled

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    德
    0.52
    мін
    0.46
    ที
    0.45
    ✉
    0.45
    ﹂
    0.45
    统一
    0.44
    线
    0.43
    经验
    0.43
    antwoord
    0.42
    алы
    0.42
    POSITIVE LOGITS
     oxidative
    0.50
     hci
    0.49
     depriving
    0.49
     plagued
    0.48
     ∀
    0.45
     bitrate
    0.45
     altitude
    0.44
     permeates
    0.44
     disconcert
    0.44
     sported
    0.44
    Activations Density 0.006%

    No Known Activations