© 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. 75092
    Prev
    Next
    INDEX
    Explanations

    time before, during, and after events

    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
     появился
    -1.05
     ابتدا
    -1.05
     velha
    -0.94
    襤
    -0.92
    こんな感じで
    -0.91
     fatica
    -0.90
     sinnvoll
    -0.90
     suna
    -0.89
     laquelle
    -0.89
    grado
    -0.89
    POSITIVE LOGITS
     during
    1.92
     when
    1.45
     after
    1.27
     दौरान
    1.24
     throughout
    1.21
     before
    1.18
     During
    1.13
     أثناء
    1.09
     until
    1.02
     later
    1.01
    Activations Density 0.060%

    No Known Activations