© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 79283
    Prev
    Next
    INDEX
    Explanations

    prosthetic and orthopedic devices

    np_acts-logits-general · gemini-2.5-flash-lite

    medical and prosthetic terminology, especially related to artificial limbs and assistive devices.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MUS
    -0.80
     LUX
    -0.78
     ORGAN
    -0.77
     Lasse
    -0.76
     Niro
    -0.76
    tieth
    -0.75
     EMF
    -0.75
    newBuilder
    -0.74
     arab
    -0.73
    styp
    -0.73
    POSITIVE LOGITS
     patients
    1.21
     patient
    1.18
     Patients
    1.14
     fabrication
    1.02
     pacientes
    1.00
    Patient
    0.99
     Patient
    0.98
     socket
    0.96
    patient
    0.93
     Anpass
    0.89
    Activations Density 0.032%

    No Known Activations