© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 1044
    Prev
    Next
    INDEX
    Explanations

    blood measurements and levels

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

    medical readings and levels

    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
     масштаб
    0.51
     incumb
    0.48
    ან
    0.48
    င်္ဂ
    0.47
     റോ
    0.47
     operazioni
    0.46
     തൊഴിലാ
    0.46
    텀
    0.46
     ფედერ
    0.46
    财务
    0.45
    POSITIVE LOGITS
     levels
    1.81
     niveles
    1.55
    levels
    1.52
     serum
    1.51
     elevated
    1.49
     Levels
    1.46
     níveis
    1.46
     blood
    1.45
     readings
    1.41
    Levels
    1.34
    Activations Density 0.186%

    No Known Activations