© 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. 8425
    Prev
    Next
    INDEX
    Explanations

    cardiac and cholesterol conditions

    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
     encephal
    0.46
     ICF
    0.45
     encephalitis
    0.42
     tremors
    0.41
    雏
    0.40
     relay
    0.40
    鞠
    0.39
     immunore
    0.38
     neonatal
    0.38
    捣
    0.38
    POSITIVE LOGITS
     cholesterol
    1.13
     Cholesterol
    1.13
     colesterol
    1.09
     plaque
    1.08
     LDL
    1.04
     atheros
    1.02
     ather
    0.97
     atherosclerosis
    0.96
     cholester
    0.95
     artery
    0.90
    Activations Density 0.176%

    No Known Activations