© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 5961
    Prev
    Next
    INDEX
    Explanations

    -ize verbs and suffixes

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

    verbs and nouns ending in -ize or -ization

    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
    точные
    0.39
    ຖ
    0.38
    ْس
    0.37
    atalog
    0.37
     හැකිය
    0.37
    ่ว
    0.35
    ্বল
    0.35
    ্ের
    0.35
    घी
    0.35
    お願いします
    0.34
    POSITIVE LOGITS
    ization
    3.67
    izing
    3.56
    ized
    3.53
    izations
    3.27
    isation
    3.22
    ize
    3.08
    化的
    3.06
    化
    3.05
    izer
    3.00
    izes
    2.97
    Activations Density 0.175%

    No Known Activations