© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47414
    Prev
    Next
    INDEX
    Explanations

    compile, Compilation, Compiler

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wohin
    -1.09
    '
    -1.07
    ichier
    -1.06
     know
    -1.05
     womit
    -1.04
     diversa
    -1.02
     fulfilling
    -1.01
    $,
    -1.01
     tell
    -1.01
     raí
    -0.98
    POSITIVE LOGITS
     Compilation
    1.09
    넴
    1.06
    ugeot
    1.06
    
    1.05
     COMP
    1.05
     Comp
    1.05
     Compile
    1.03
    Touched
    1.02
     Corbu
    0.98
    ᚖ
    0.98
    Activations Density 0.023%

    No Known Activations