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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 16-GEMMASCOPE-2-RES-16K
    7. 435
    Prev
    Next
    INDEX
    Explanations

    Christianity

    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_16_width_16k_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
    របស់
    0.45
     раст
    0.44
     број
    0.44
     sépt
    0.44
    í
    0.44
    స్
    0.43
     країн
    0.42
    icios
    0.41
    ités
    0.41
    itories
    0.41
    POSITIVE LOGITS
    ↵
    0.68
     Jesus
    0.55
    </h4>
    0.52
     God
    0.51
     Religion
    0.50
     Theology
    0.50
     Church
    0.49
     has
    0.49
     Scriptures
    0.48
     Jezus
    0.47
    Activations Density 1.422%

    No Known Activations