© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111717
    Prev
    Next
    INDEX
    Explanations

    Jesus Christ passion sacrifice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⁴
    -1.47
     kunst
    -1.45
    comes
    -1.45
    biendo
    -1.33
    quire
    -1.31
     nimmer
    -1.29
     cán
    -1.27
     treff
    -1.27
    uding
    -1.26
    :「
    -1.26
    POSITIVE LOGITS
     kurzen
    1.20
     falschen
    1.17
    ↵↵
    1.17
     Öffentlich
    1.11
     wichtigen
    1.10
     Männern
    1.09
     Verständnis
    1.08
     paramount
    1.05
    行った
    1.04
    penters
    1.03
    Activations Density 0.020%

    No Known Activations