© 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. 45597
    Prev
    Next
    INDEX
    Explanations

    regular expressions

    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
    ৄ
    -2.95
     所以
    -2.55
    皤
    -2.50
    勦
    -2.50
     它
    -2.48
     而
    -2.28
    n
    -2.27
    0
    -2.06
     这
    -1.97
     Instead
    -1.95
    POSITIVE LOGITS
    ↵
    2.61
    
    2.17
     we
    2.09
    ischof
    2.08
     diseñada
    2.03
    饜
    2.02
    alakip
    2.02
    镚
    2.00
    $
    1.99
     estándares
    1.97
    Activations Density 0.005%

    No Known Activations