© 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. 48050
    Prev
    Next
    INDEX
    Explanations

    android system services

    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
    s
    -1.84
     everybody
    -1.42
     beyond
    -1.38
    !",
    -1.37
    in
    -1.34
    ."]
    -1.30
    ."<
    -1.30
     ?"
    -1.28
    !),
    -1.28
    
    -1.27
    POSITIVE LOGITS
    tersebut
    1.45
    Totally
    1.28
    ’
    1.27
     őket
    1.27
    Cevap
    1.23
    phòng
    1.23
    ihnachts
    1.21
    鹋
    1.18
    Completely
    1.18
    انواع
    1.17
    Activations Density 0.013%

    No Known Activations