© 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. 22-GEMMASCOPE-RES-131K
    7. 64625
    Prev
    Next
    INDEX
    Explanations

    programming keywords and variables

    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_22/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
    dasarkan
    -1.02
    maphore
    -0.93
    iverr
    -0.91
     Sweatshirt
    -0.90
    不能为空
    -0.90
     препарат
    -0.89
    Semaphore
    -0.88
    蒙
    -0.87
    城的
    -0.87
    хео
    -0.87
    POSITIVE LOGITS
     example
    0.99
     przykład
    0.91
     ordinaria
    0.87
     puo
    0.85
     anyone
    0.85
    ショナル
    0.84
     many
    0.81
    ↵↵
    0.81
     přístup
    0.81
    ⅾ
    0.80
    Activations Density 0.031%

    No Known Activations