© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57638
    Prev
    Next
    INDEX
    Explanations

    Luke chapter:verse

    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_34/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
     ללא
    -0.85
     Baltimore
    -0.81
    CEA
    -0.74
    UserController
    -0.74
    tuber
    -0.73
    aisons
    -0.72
    TypeService
    -0.72
     Schritt
    -0.71
    )<\
    -0.71
    mitsub
    -0.71
    POSITIVE LOGITS
     Luke
    1.17
     Xcode
    0.94
     feux
    0.92
    Luke
    0.89
    Vog
    0.81
    Lk
    0.77
     Luk
    0.76
     conviene
    0.75
     Κα
    0.75
     decreto
    0.75
    Activations Density 0.007%

    No Known Activations