© 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. 36420
    Prev
    Next
    INDEX
    Explanations

    block, ore, or star identifiers

    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
    henden
    -1.11
    ález
    -1.06
    ᆺ
    -1.05
     one
    -1.04
     изображения
    -1.03
    opheles
    -1.02
    digung
    -1.02
    ditionally
    -1.02
    rictive
    -1.02
    xffff
    -1.00
    POSITIVE LOGITS
    
    1.05
    处于
    1.04
    руктура
    0.98
     lebt
    0.97
     abnormality
    0.96
     订单
    0.95
     客户
    0.94
    ธอ
    0.94
     erneut
    0.94
     первой
    0.93
    Activations Density 0.001%

    No Known Activations