© 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-65K
    7. 4291
    Prev
    Next
    INDEX
    Explanations

    our team, customers, users, experts

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     वीडियो
    0.44
    videos
    0.44
     видео
    0.44
     videos
    0.42
     videomuz
    0.41
     top
    0.41
    動画
    0.41
    ^_
    0.41
     فيديو
    0.41
    video
    0.40
    POSITIVE LOGITS
     panel
    0.63
     Panel
    0.59
     especialistas
    0.57
     Experts
    0.55
    Panel
    0.54
     panelists
    0.54
     PANEL
    0.52
    experts
    0.51
    panel
    0.50
     expertos
    0.50
    Activations Density 0.001%

    No Known Activations