© 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. 41986
    Prev
    Next
    INDEX
    Explanations

    RFID technology and applications

    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
    </b>
    -2.80
     ---
    -2.72
     This
    -2.72
    </h4>
    -2.56
    l
    -2.55
    ꦢ
    -2.53
    м
    -2.50
     ['./
    -2.42
     для
    -2.41
     dieser
    -2.41
    POSITIVE LOGITS
     drit
    2.70
    鬭
    2.66
    
    2.38
    一块
    2.33
    阏
    2.30
     frequentemente
    2.23
    鮰
    2.22
     heo
    2.20
    鲩
    2.20
     排骨
    2.17
    Activations Density 0.013%

    No Known Activations