© 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. 79494
    Prev
    Next
    INDEX
    Explanations

    apparently or otherwise healthy

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Negative Logits
     žá
    -0.79
    stubs
    -0.75
    onday
    -0.73
     McP
    -0.70
     süß
    -0.70
    ųjų
    -0.69
     rychle
    -0.69
    Ɣ
    -0.68
     comprensión
    -0.67
     víc
    -0.67
    POSITIVE LOGITS
     healthy
    7.44
    healthy
    6.19
    Healthy
    5.78
     Healthy
    5.75
     healthier
    4.41
     здоро
    4.28
     healthiest
    3.95
    健康
    3.64
     HEALTH
    3.52
    HEALTH
    3.34
    Activations Density 0.298%

    No Known Activations