© 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. 47263
    Prev
    Next
    INDEX
    Explanations

    while loop

    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
    Negative Logits
     devrait
    -0.89
     geométrico
    -0.87
     afecto
    -0.86
    忙
    -0.85
     poate
    -0.82
    ioutil
    -0.79
     McCl
    -0.78
    adapt
    -0.78
    ėjimo
    -0.78
    fatt
    -0.77
    POSITIVE LOGITS
     ($
    1.10
    List
    1.05
     list
    1.05
     List
    1.03
    list
    1.02
    (($
    0.88
    ($
    0.85
    MouseMove
    0.84
    LIST
    0.84
     ($\
    0.75
    Activations Density 0.007%

    No Known Activations