© 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. 15563
    Prev
    Next
    INDEX
    Explanations

    for loops

    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
     =
    -2.30
     gets
    -2.14
    拶
    -2.08
     was
    -2.05
     as
    -1.92
     ensures
    -1.84
     زیرا
    -1.82
     believes
    -1.81
     described
    -1.80
     However
    -1.78
    POSITIVE LOGITS
    灕
    2.27
    selben
    2.03
    焢
    1.98
    媄
    1.92
    ↵
    1.88
    鈊
    1.88
    摃
    1.88
     土産
    1.88
    1.83
    
    1.80
    Activations Density 0.003%
    No Known Activations