© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 3369
    Prev
    Next
    INDEX
    Explanations

    religious doctrine and theology

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     눈
    0.87
     sabiduría
    0.86
     샘
    0.86
     tmp
    0.83
     마을
    0.82
     삶
    0.80
     영향
    0.80
    冥
    0.80
     pavil
    0.79
     영역
    0.78
    POSITIVE LOGITS
     doctr
    1.21
     doctrine
    1.19
     doctrinal
    1.11
    Doctrine
    1.10
     Doctrine
    1.08
    doctrine
    1.08
     theological
    1.00
     theology
    1.00
     doctrina
    0.98
     doctrines
    0.98
    Activations Density 0.080%

    No Known Activations