© 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. 40-GEMMASCOPE-2-RES-65K
    7. 55511
    Prev
    Next
    INDEX
    Explanations

    Python ArgumentParser

    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_40_width_65k_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
     elect
    0.45
     convert
    0.39
     conductor
    0.39
     συ
    0.39
     ilus
    0.39
     h
    0.38
     illusions
    0.38
     brig
    0.38
     sub
    0.38
     get
    0.38
    POSITIVE LOGITS
     wavenumber
    0.40
    㬹
    0.40
    TargetFramework
    0.39
    侬
    0.39
    НО
    0.39
     Depending
    0.38
    lastname
    0.38
     ರೆ
    0.38
    Ȼ
    0.38
     المبلغ
    0.37
    Activations Density 0.001%

    No Known Activations