© 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. 31-GEMMASCOPE-2-RES-262K
    7. 9578
    Prev
    Next
    INDEX
    Explanations

    numbered list item 1

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Sh
    0.41
    As
    0.40
    W
    0.39
    Column
    0.37
    Weighted
    0.36
    Ab
    0.35
    Windows
    0.35
    Resolution
    0.35
    Sub
    0.35
    Detailed
    0.35
    POSITIVE LOGITS
    atgu
    0.49
     यानी
    0.48
     //=>
    0.46
     우리
    0.45
     --->
    0.45
    --->
    0.43
     décisions
    0.43
     wollen
    0.43
    <0x0B>
    0.42
     시장
    0.42
    Activations Density 0.029%

    No Known Activations