© 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. 45542
    Prev
    Next
    INDEX
    Explanations

    this week/year

    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
     and
    -2.77
     of
    -2.11
     by
    -2.00
     nestled
    -1.91
     burgeoning
    -1.90
    zegovina
    -1.87
     και
    -1.86
     longstanding
    -1.85
     for
    -1.80
    ၃
    -1.77
    POSITIVE LOGITS
    0
    2.77
    1
    2.05
    吃到
    1.98
    ⏑
    1.92
    シャレ
    1.91
     incredi
    1.81
     exercer
    1.80
    6
    1.76
    辇
    1.75
    桖
    1.75
    Activations Density 0.029%

    No Known Activations