© 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-IT
    3. 41-GEMMASCOPE-2-RES-262K
    4. 101
    Prev
    Next
    INDEX
    Explanations

    badminton players and Indonesian cities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     উৎকৃষ্ট
    0.65
     operable
    0.57
    鹼
    0.57
    閾
    0.55
    จุบัน
    0.55
    โยชน์
    0.54
     एग्जांपल
    0.53
    ﻠ
    0.53
     সংকোচন
    0.52
     এরূপ
    0.52
    POSITIVE LOGITS
     rued
    0.73
     debut
    0.70
     Badminton
    0.68
     Selangor
    0.66
     pemain
    0.64
     badminton
    0.64
     Indonesia
    0.63
     Jakarta
    0.62
     Kuala
    0.62
     Sekolah
    0.62
    Activations Density 0.002%

    No Known Activations