© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 8314
    Prev
    Next
    INDEX
    Explanations

    religious and philosophical ideas

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

    philosophies, doctrines, and ideologies

    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_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    备注
    0.44
    ুকু
    0.43
     строку
    0.41
    博物馆
    0.41
     गर
    0.40
     situazioni
    0.40
     ಅನುಪಾತ
    0.39
    靥
    0.39
     Qualifier
    0.39
     আয়োজন
    0.38
    POSITIVE LOGITS
     philosophies
    1.56
     doctrines
    1.52
     philosophy
    1.39
     ideology
    1.30
     ideologies
    1.30
     doctrine
    1.26
     filosofía
    1.23
     философия
    1.23
     theories
    1.23
     teachings
    1.20
    Activations Density 0.433%

    No Known Activations