© 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-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 37845
    Prev
    Next
    INDEX
    Explanations

    their/there/they're homophones

    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
    制定
    0.46
    ാവ്
    0.44
     pitting
    0.43
    ⱪ
    0.40
    LQ
    0.40
     Kazim
    0.39
     variétés
    0.39
     Provided
    0.38
     raus
    0.38
    щ
    0.38
    POSITIVE LOGITS
     particular
    0.86
    selves
    0.77
     own
    0.73
    particular
    0.72
     particulares
    0.71
     particolare
    0.70
     particulière
    0.62
    Particular
    0.61
     utmost
    0.60
     particulier
    0.59
    Activations Density 0.003%

    No Known Activations