© 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-262K
    7. 12882
    Prev
    Next
    INDEX
    Explanations

    assumptions and idealized models

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     اجر
    0.48
     सेंचुरी
    0.47
     tầm
    0.47
    运营
    0.45
     Supervision
    0.43
    Certification
    0.43
    ފައި
    0.43
    Stake
    0.43
    তাহাকে
    0.42
    ╹
    0.42
    POSITIVE LOGITS
     idealized
    1.08
     ideal
    1.03
     theory
    1.00
     classical
    1.00
    理想
    0.95
    ideal
    0.95
     assuming
    0.93
     assumes
    0.93
     teoria
    0.89
     이론
    0.88
    Activations Density 0.035%

    No Known Activations