© 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. 21731
    Prev
    Next
    INDEX
    Explanations

    wearing clothes or accessories

    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
     \
    -2.92
    \
    -2.75
     itinerario
    -2.63
     seems
    -2.53
    which
    -2.48
     they
    -2.42
    琑
    -2.39
    鈰
    -2.38
     enjoys
    -2.36
    arraycopy
    -2.34
    POSITIVE LOGITS
     They
    3.22
    罴
    3.00
    sudadera
    2.88
     generando
    2.56
    烀
    2.53
    羮
    2.47
    趼
    2.45
     estando
    2.42
     übernahm
    2.42
     Their
    2.34
    Activations Density 0.008%

    No Known Activations