© 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. 39874
    Prev
    Next
    INDEX
    Explanations

    HTML spacing and line breaks

    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
    Библи
    -1.09
    違和
    -1.08
    assistance
    -1.07
    揶
    -1.05
    囁
    -1.04
     bygga
    -1.02
    sự
    -1.01
    憔
    -1.00
     akrab
    -1.00
     mobilya
    -1.00
    POSITIVE LOGITS
    。　
    1.02
     again
    0.99
     ہیں۔
    0.95
    вания
    0.93
    duino
    0.93
     față
    0.93
     ڈ
    0.91
     вдруг
    0.90
     and
    0.88
    Algérie
    0.87
    Activations Density 0.003%

    No Known Activations