© 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. 4592
    Prev
    Next
    INDEX
    Explanations

    jewelry and accessories

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

    jewelry and jewels

    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
    🚌
    0.46
     frigor
    0.44
    ِّف
    0.43
    舸
    0.42
    檗
    0.42
    翛
    0.41
    नून
    0.41
    mUserManager
    0.41
    汾
    0.41
     गी
    0.41
    POSITIVE LOGITS
     jewelry
    2.66
     jewellery
    2.58
     necklace
    2.48
     necklaces
    2.47
     Jewelry
    2.45
    jewelry
    2.39
     earrings
    2.34
     Jewellery
    2.33
     bracelet
    2.31
     bracelets
    2.20
    Activations Density 0.310%

    No Known Activations