© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5668
    Prev
    Next
    INDEX
    Explanations

    pants and shorts

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

    pants, trousers, shorts, jeans

    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
     halo
    0.41
     सर्टिफिकेट
    0.38
     Hald
    0.38
    釧
    0.38
     स्टेशनों
    0.38
    SimpleDateFormat
    0.37
     Iterator
    0.37
    振り
    0.37
     certificate
    0.36
     Halo
    0.36
    POSITIVE LOGITS
     pants
    2.81
     trousers
    2.59
     Pants
    2.50
    裤
    2.44
    褲
    2.33
     shorts
    2.28
     pantalones
    2.28
    pants
    2.27
    パンツ
    2.22
     jeans
    2.13
    Activations Density 0.115%

    No Known Activations