© 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. 12864
    Prev
    Next
    INDEX
    Explanations

    benchmarks and experimental results

    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
     appren
    0.44
    信息的
    0.40
    aprend
    0.38
    เรียน
    0.38
    ीत
    0.37
     begrij
    0.37
    엘
    0.37
     renounce
    0.36
     एडज
    0.36
    ච
    0.36
    POSITIVE LOGITS
     benchmarks
    1.16
     benchmark
    1.13
     benchmarking
    1.03
     evaluation
    1.01
    benchmark
    0.99
     evaluations
    0.97
     experiments
    0.95
     comparison
    0.94
     comparisons
    0.94
     evaluated
    0.92
    Activations Density 0.033%

    No Known Activations