© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 2854
    Prev
    Next
    INDEX
    Explanations

    types of clothing

    np_acts-logits-general · gemini-2.5-flash-lite

    clothes and garments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âns
    0.42
     দাত
    0.41
    橼
    0.40
     epicenter
    0.38
    dió
    0.38
    四大
    0.37
    伺
    0.37
    顐
    0.37
     guarante
    0.36
     അപ
    0.36
    POSITIVE LOGITS
     sweater
    1.71
     cardigan
    1.63
     sweaters
    1.55
     sweatshirt
    1.55
     blouse
    1.54
     turtleneck
    1.52
     blazer
    1.48
    sweater
    1.48
     blouses
    1.47
     shirt
    1.45
    Activations Density 0.275%

    No Known Activations