© 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
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5222
    Prev
    Next
    INDEX
    Explanations

    anatomical tissues and structures

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

    biological anatomy and structures

    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
     финансо
    0.64
    栆
    0.62
     yaşanan
    0.57
     سیاسی
    0.56
     कारगर
    0.56
     وګټ
    0.56
    堣
    0.56
    ủi
    0.55
    上涨
    0.55
     незакон
    0.55
    POSITIVE LOGITS
     anatom
    1.22
     anatomical
    1.18
     innervation
    1.16
     epithelium
    1.15
     anatomic
    1.07
     cranial
    1.05
     dorsal
    1.03
     ventral
    1.03
     caudal
    1.03
    anatom
    1.03
    Activations Density 0.065%

    No Known Activations