© 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. 10-GEMMASCOPE-RES-131K
    7. 15574
    Prev
    Next
    INDEX
    Explanations

    coding assertions or definitions

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     I
    -1.51
     &
    -1.51
    $
    -1.51
    d
    -1.42
     FOR
    -1.34
     for
    -1.33
     know
    -1.31
     don
    -1.29
     Just
    -1.29
     \
    -1.28
    POSITIVE LOGITS
     можем
    1.70
     Perſ
    1.52
     Conſ
    1.52
    灕
    1.52
    objets
    1.52
    菹
    1.51
    
    1.49
     orgánica
    1.43
     داریم
    1.43
    Gestion
    1.41
    Activations Density 0.005%

    No Known Activations