© 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. 17632
    Prev
    Next
    INDEX
    Explanations

    signs and wonders

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

    supernatural and miraculous events

    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
    胥
    0.47
     ಗೌ
    0.44
     eternally
    0.41
     दुर्ग
    0.40
     getpath
    0.40
     मज
    0.38
     buffer
    0.38
     беско
    0.38
    岌
    0.37
    alignParent
    0.37
    POSITIVE LOGITS
     miracle
    1.45
     miracles
    1.44
     miraculous
    1.35
     mirac
    1.27
     supernatural
    1.27
     Miracle
    1.23
     चमत्कार
    1.20
     miraculously
    1.13
     Supernatural
    1.05
     чудо
    1.00
    Activations Density 0.109%

    No Known Activations