© 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-16K
    7. 10991
    Prev
    Next
    INDEX
    Explanations

    Executive Summary

    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_16k_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
     Reve
    0.42
     Sex
    0.41
    覧
    0.41
     Cite
    0.41
     Reformation
    0.40
     rev
    0.39
     Troubles
    0.39
     Physician
    0.39
     Scot
    0.39
     y
    0.38
    POSITIVE LOGITS
    Executive
    0.71
     executive
    0.64
     Executive
    0.61
    executive
    0.61
     EXECUTIVE
    0.55
     pallet
    0.49
     ejecutivo
    0.47
    pallet
    0.45
    Snapped
    0.45
     कार्यकारी
    0.44
    Activations Density 0.029%

    No Known Activations