© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 8599
    Prev
    Next
    INDEX
    Explanations

    indentation

    np_acts-logits-general · gemini-2.5-flash-lite

    code indentation and formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     stimul
    0.40
     dissemin
    0.39
    ಳಗ
    0.38
    uan
    0.38
     Nxf
    0.38
    alla
    0.38
     pavatt
    0.37
     thải
    0.36
     मृत्यु
    0.36
    榭
    0.36
    POSITIVE LOGITS
     indent
    3.22
    indent
    3.11
    Indent
    3.05
     indentation
    2.95
     indented
    2.70
     dent
    2.27
     indenture
    2.11
     dents
    2.03
     Dent
    1.87
    dent
    1.82
    Activations Density 0.018%

    No Known Activations