© 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. 26791
    Prev
    Next
    INDEX
    Explanations

    mathematical or code structures

    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
    糴
    -1.10
     fiabilidad
    -1.08
    从来
    -1.08
    もしれません
    -1.08
     praktische
    -1.02
    לון
    -1.02
     conster
    -0.96
     INFLU
    -0.93
    すべての
    -0.92
     抠
    -0.91
    POSITIVE LOGITS
    ﴾
    1.13
     other
    1.13
     inaprop
    1.10
     Pittsburgh
    1.03
    ChatColor
    1.01
    титься
    1.00
    TextSpan
    1.00
     utama
    0.98
      
    0.98
    ITÀ
    0.97
    Activations Density 0.296%

    No Known Activations