© 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. 53-GEMMASCOPE-2-RES-262K
    4. 13557
    Prev
    Next
    INDEX
    Explanations

    galaxies and galaxy

    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/layer_53_width_262k_l0_medium
    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
    哏
    0.42
     কমান্ডার
    0.42
     Venus
    0.41
     koncept
    0.41
     planter
    0.41
    钮
    0.40
     Plantation
    0.40
     Цу
    0.39
    铯
    0.39
     Ober
    0.39
    POSITIVE LOGITS
     galaxy
    1.96
     galaxies
    1.86
    galaxy
    1.80
    Galaxy
    1.71
     галакти
    1.69
     Galaxy
    1.68
     Galaxies
    1.54
     galactic
    1.36
     갤럭시
    1.34
    galax
    1.26
    Activations Density 0.017%

    No Known Activations