© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 2737
    Prev
    Next
    INDEX
    Explanations

    transplant or implant body parts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
     Untersuch
    0.76
    挠
    0.74
     binoculars
    0.73
    琐
    0.72
     interpretación
    0.72
     turbulence
    0.71
     सर्वेक्षण
    0.71
    📘
    0.70
    警戒
    0.70
     Turbulent
    0.69
    POSITIVE LOGITS
     transplant
    1.96
     transplantation
    1.89
     transplants
    1.87
     implants
    1.85
     implant
    1.77
     implanted
    1.72
     Implant
    1.68
     transplanted
    1.66
     Transplant
    1.62
     implantation
    1.54
    Activations Density 0.193%

    No Known Activations