© 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. 72027
    Prev
    Next
    INDEX
    Explanations

    locations and associated descriptors

    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
    ❓
    -1.45
     luxo
    -1.44
    ܜ
    -1.43
     anla
    -1.41
    还有一个
    -1.40
     یکی
    -1.40
     asisten
    -1.40
    ₂,
    -1.39
    swire
    -1.38
     ɛ
    -1.37
    POSITIVE LOGITS
     approach
    1.89
    7
    1.88
     that
    1.77
     experience
    1.75
    8
    1.53
     system
    1.52
     arrangement
    1.52
     way
    1.52
     section
    1.48
     account
    1.48
    Activations Density 0.847%

    No Known Activations