© 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. 56294
    Prev
    Next
    INDEX
    Explanations

    working prototype concepts

    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
     mek
    0.41
     tér
    0.40
     Worcestershire
    0.39
     Hug
    0.39
    格局
    0.39
     geografia
    0.39
    wsgi
    0.39
     marginal
    0.38
    alay
    0.38
    侪
    0.38
    POSITIVE LOGITS
     prototype
    1.04
     prototypes
    1.03
     concept
    1.00
    Concept
    0.96
    概念
    0.95
     concepts
    0.95
     Concept
    0.94
    concept
    0.92
    prototype
    0.91
    Concepts
    0.90
    Activations Density 0.040%

    No Known Activations