© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5850
    Prev
    Next
    INDEX
    Explanations

    healthy or healthier states

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

    healthy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     専用
    0.42
    မ့်
    0.37
     invariance
    0.36
     Explicit
    0.36
    tabPadding
    0.35
    蜴
    0.35
    Explicit
    0.34
    績
    0.34
    explicit
    0.33
     explicit
    0.33
    POSITIVE LOGITS
     healthy
    4.94
    healthy
    4.66
    Healthy
    4.53
     Healthy
    4.41
     здоро
    4.25
     sağlıklı
    3.89
     healthier
    3.81
     स्वस्थ
    3.80
     sehat
    3.72
     healthiest
    3.56
    Activations Density 0.179%

    No Known Activations