© 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. 26315
    Prev
    Next
    INDEX
    Explanations

    axis properties

    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
    ងឺ
    0.45
    пии
    0.40
    ียม
    0.39
    érieure
    0.39
    Comfort
    0.39
    LIMIT
    0.38
    ﻳ
    0.38
    手に
    0.38
    Target
    0.38
     بابەت
    0.38
    POSITIVE LOGITS
     축
    0.44
     Comer
    0.42
     Rectangle
    0.41
     Angus
    0.40
     AMD
    0.39
     barg
    0.38
     अब्दु
    0.38
     Airline
    0.38
     Retina
    0.37
     Comedy
    0.37
    Activations Density 0.002%

    No Known Activations