© 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. 69529
    Prev
    Next
    INDEX
    Explanations

    mermaids, nymphs, and princesses

    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
     también
    -2.44
    袮
    -2.41
     vorliegenden
    -2.36
     også
    -2.30
    相同
    -2.28
     aérienne
    -2.23
    .")
    -2.20
    就
    -2.17
     älskar
    -2.17
    как
    -2.16
    POSITIVE LOGITS
    鸯
    2.45
    臜
    2.30
    ༵
    2.25
     měla
    2.05
     coloridos
    1.98
    
    1.96
    驀
    1.95
     creó
    1.93
    鉝
    1.90
    蜮
    1.89
    Activations Density 0.001%

    No Known Activations