© 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. 10-GEMMASCOPE-RES-131K
    7. 42681
    Prev
    Next
    INDEX
    Explanations

    months and dates

    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_10/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
     Não
    -1.88
    jstor
    -1.84
    
    -1.80
     geprü
    -1.77
    dede
    -1.74
    <
    -1.74
     所以
    -1.73
    führen
    -1.71
    ༣
    -1.69
     también
    -1.68
    POSITIVE LOGITS
    ↵
    2.98
     vorigen
    1.88
    Pä
    1.71
    坼
    1.69
    ズニー
    1.67
    鿬
    1.66
    ization
    1.63
     <",
    1.62
    今月
    1.62
    骓
    1.61
    Activations Density 0.004%

    No Known Activations