© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 64490
    Prev
    Next
    INDEX
    Explanations

    swelling or puffing out

    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
     NICKEL
    0.42
    служ
    0.41
     vitesses
    0.40
    桫
    0.39
     сни
    0.39
     हिमालय
    0.39
    ্ু
    0.39
    Narrow
    0.39
    畿
    0.39
     consola
    0.38
    POSITIVE LOGITS
     swelling
    1.54
     swollen
    1.46
     swelled
    1.38
     bulging
    1.38
    膨
    1.38
     swell
    1.34
     swells
    1.32
     bulge
    1.21
    胀
    1.17
     inflated
    1.16
    Activations Density 0.006%

    No Known Activations