© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 39288
    Prev
    Next
    INDEX
    Explanations

    past tense actions and 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
     {
    
    -1.04
    关于
    -0.99
     гораздо
    -0.90
    áis
    -0.90
     kristal
    -0.88
    Similarly
    -0.87
     kampus
    -0.87
     atlet
    -0.86
    Featuring
    -0.85
    Приятного
    -0.85
    POSITIVE LOGITS
     melindungi
    1.13
     وزار
    1.13
     mengurangi
    1.12
     MemoryStream
    1.08
     setw
    1.05
     slated
    1.05
    tabria
    1.05
     تكون
    1.04
    Norge
    1.03
    ylvania
    1.01
    Activations Density 0.051%

    No Known Activations