© 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. 4183
    Prev
    Next
    INDEX
    Explanations

    package main

    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
    Not in Any Lists

    No Comments

    Negative Logits
    CellStyle
    0.43
    高志森
    0.43
    FontSize
    0.41
    AlH
    0.40
     म
    0.39
     <*>
    0.39
    ボ
    0.39
    Bott
    0.38
    hém
    0.38
     '))
    0.38
    POSITIVE LOGITS
     main
    0.52
     PACKAGE
    0.45
    main
    0.43
     com
    0.42
     programmers
    0.40
     główn
    0.40
    课
    0.39
     Homework
    0.39
     testclass
    0.39
     JAVA
    0.38
    Activations Density 0.005%

    No Known Activations