© 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-262K
    7. 1593
    Prev
    Next
    INDEX
    Explanations

    mobility aids and wheeled transport

    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_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
     bioinformatics
    0.54
     virulent
    0.52
     disillusioned
    0.51
     apoptosis
    0.48
     cynical
    0.48
     detoxification
    0.48
     seroton
    0.47
    🧬
    0.47
     polluted
    0.47
     disinformation
    0.47
    POSITIVE LOGITS
     wheeled
    1.47
     wheelchairs
    1.37
     wheelchair
    1.33
     wheels
    1.25
    wheeled
    1.15
     wheel
    1.13
     Wheels
    1.11
     mobility
    1.10
    wheels
    1.09
     carts
    1.05
    Activations Density 0.019%

    No Known Activations