© 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. 803
    Prev
    Next
    INDEX
    Explanations

    city names and city

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

    city

    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
     Bxg
    0.41
     peroxidase
    0.38
    adura
    0.37
     calomel
    0.37
     glPushMatrix
    0.36
     Normdatei
    0.36
    酵素
    0.36
    𒄩
    0.35
    थमिक
    0.34
     मायणी
    0.34
    POSITIVE LOGITS
     city
    4.97
    city
    4.44
     शहर
    4.16
    City
    4.00
     città
    4.00
     City
    3.95
     CITY
    3.91
     ciudad
    3.89
     cidade
    3.89
    CITY
    3.86
    Activations Density 0.629%

    No Known Activations