© 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. 41-GEMMASCOPE-2-RES-262K
    7. 9571
    Prev
    Next
    INDEX
    Explanations

    official online applications and fees

    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_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     isotropy
    0.54
     conductivity
    0.52
     orthogonal
    0.51
    brightness
    0.51
     isotropic
    0.51
    装着
    0.50
     macroscopic
    0.50
     déploy
    0.50
     ആക്രമ
    0.50
     乀
    0.49
    POSITIVE LOGITS
     official
    1.01
     Official
    0.97
    Official
    0.96
    Fees
    0.90
     deadlines
    0.89
     Fees
    0.88
     oficial
    0.86
    official
    0.86
     официа
    0.86
     fees
    0.85
    Activations Density 0.001%

    No Known Activations