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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39820
    Prev
    Next
    INDEX
    Explanations

    programming language elements

    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
    Leírás
    -1.49
    
    -1.14
     العديد
    -1.13
    푉
    -1.13
    توضیحات
    -1.13
     jeweiligen
    -1.10
     Även
    -1.09
    addTab
    -1.07
    MILLISECONDS
    -1.04
     Некоторые
    -1.03
    POSITIVE LOGITS
     such
    1.07
     hábit
    0.98
     mê
    0.97
     Amad
    0.97
     libre
    0.97
     (
    0.96
     pries
    0.95
     mantenga
    0.94
     lettre
    0.93
     núm
    0.93
    Activations Density 0.000%

    No Known Activations