© 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. 113910
    Prev
    Next
    INDEX
    Explanations

    popular items and topics

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ⻬
    -2.47
     cincuenta
    -2.17
     verdaderamente
    -2.14
     sneak
    -2.14
     efectu
    -2.11
     usado
    -2.11
     turbulent
    -2.08
     regroupe
    -2.08
    
    -2.06
     maravillosas
    -2.05
    POSITIVE LOGITS
    禤
    2.88
    塤
    2.77
    0
    2.53
    W
    2.50
    M
    2.48
    H
    2.44
    .
    2.44
     می‌شوند
    2.38
    蒹
    2.38
    3
    2.34
    Activations Density 0.009%

    No Known Activations