© 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. 75162
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming terms

    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
    樞
    -0.81
     cc
    -0.79
     galite
    -0.78
    cmt
    -0.78
    ediakan
    -0.78
    Album
    -0.77
     suspensión
    -0.77
    但
    -0.77
    ait
    -0.75
    瀾
    -0.75
    POSITIVE LOGITS
    Скачать
    0.96
    finalize
    0.90
     disreg
    0.84
    ENDER
    0.84
     리스트
    0.83
     lastly
    0.83
     flashbacks
    0.81
    PARE
    0.81
    ابقة
    0.80
    емости
    0.80
    Activations Density 0.004%

    No Known Activations