© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26099
    Prev
    Next
    INDEX
    Explanations

    programming keywords and types

    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
    さらに
    -1.05
    新的
    -0.98
     おすすめ
    -0.94
    unno
    -0.94
     conclusion
    -0.94
     remedy
    -0.92
    愷
    -0.91
     腕時計
    -0.90
    グッズ
    -0.88
     return
    -0.87
    POSITIVE LOGITS
    事です
    0.94
     posiblemente
    0.94
     tết
    0.94
    敝
    0.91
     quizás
    0.91
    atecas
    0.89
    probably
    0.88
     цве
    0.87
     HY
    0.87
    ﻭ
    0.87
    Activations Density 0.027%

    No Known Activations