© 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
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 2017
    Prev
    Next
    INDEX
    Explanations

    matching information

    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
    躹
    1.34
    اکي
    1.32
    靂
    1.30
    رځ
    1.26
    ឡិច
    1.24
    ាតុ
    1.22
    ឍ
    1.19
    ្នែក
    1.16
    ઠળ
    1.16
    িকাংশ
    1.15
    POSITIVE LOGITS
     가
    1.85
     수
    1.83
    에
    1.82
    이
    1.80
     부
    1.80
    도
    1.79
     고
    1.77
    의
    1.74
     이
    1.73
     어
    1.73
    Activations Density 0.005%

    No Known Activations