© 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. 40-GEMMASCOPE-2-RES-16K
    7. 10010
    Prev
    Next
    INDEX
    Explanations

    Biblical book chapter references

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

    Bible book chapters

    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
    Not in Any Lists

    No Comments

    Negative Logits
     balo
    0.47
    ktu
    0.45
    ৭০
    0.44
     arit
    0.44
    يتي
    0.42
    ABCDEFGHIJKLMNOP
    0.42
     ["[
    0.42
    ('/\
    0.41
     komponen
    0.41
    ৪৭
    0.41
    POSITIVE LOGITS
     chapter
    0.69
    chapter
    0.68
     Chapter
    0.64
     chapitre
    0.63
     chapters
    0.58
    Chapter
    0.57
     xvii
    0.56
     capítulo
    0.53
     चैप्टर
    0.52
     xviii
    0.50
    Activations Density 0.054%

    No Known Activations