© 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. 35328
    Prev
    Next
    INDEX
    Explanations

    peeled or peeler

    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
    Kris
    0.43
     मिथुन
    0.39
     evidentiary
    0.38
    सव
    0.38
    樽
    0.37
     BSTC
    0.36
    itans
    0.36
     mutex
    0.36
     axonal
    0.36
     Kris
    0.35
    POSITIVE LOGITS
     peel
    3.63
     Peel
    3.36
     peeling
    3.34
     peeled
    3.25
     peels
    3.11
    剥
    2.58
    剝
    2.19
     Pee
    1.76
    Pe
    1.56
     Pe
    1.52
    Activations Density 0.017%

    No Known Activations