© 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. 557
    Prev
    Next
    INDEX
    Explanations

    code member access

    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
    går
    -1.15
    треть
    -1.08
    WART
    -1.07
    ДЕ
    -1.06
    лу
    -1.05
     alebo
    -1.04
     blusa
    -1.03
     növény
    -1.03
     汁
    -1.02
    kkue
    -1.02
    POSITIVE LOGITS
     also
    1.60
     همچنین
    1.23
    但却
    1.07
    Анти
    1.06
    ͋
    1.05
     vorhandenen
    1.03
    Здра
    1.03
    除此之外
    1.02
     neuesten
    1.01
     angegebenen
    1.01
    Activations Density 0.010%

    No Known Activations