© 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. 31-GEMMASCOPE-2-RES-262K
    7. 123816
    Prev
    Next
    INDEX
    Explanations

    Jesus and religious terms

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

    creation and explanation

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     против
    0.58
    RIB
    0.49
    ЗО
    0.48
    iato
    0.48
     ROUND
    0.47
    čnost
    0.47
    RIAL
    0.47
    ς
    0.46
     যুদ্ধ
    0.46
    放弃
    0.46
    POSITIVE LOGITS
     carbox
    0.46
     Bă
    0.43
     pseudos
    0.43
    ூ
    0.43
     phospholipid
    0.42
     cytoplasm
    0.41
     Refining
    0.41
     subcellular
    0.41
     Contributing
    0.41
    ூரில்
    0.40
    Activations Density 0.000%

    No Known Activations