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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59009
    Prev
    Next
    INDEX
    Explanations

    "God", "Jesus", "Christ", "Son", "Father"

    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
     telas
    -1.05
    ὠ
    -1.05
     hã
    -1.04
    ឌ
    -1.02
     ventanas
    -1.02
     drugi
    -1.02
     opciones
    -1.01
     pokoje
    -1.01
    ﻹ
    -0.99
     kılıf
    -0.98
    POSITIVE LOGITS
     And
    1.14
     then
    1.07
     seek
    1.01
     do
    0.96
     He
    0.96
     he
    0.95
     for
    0.94
     consider
    0.93
     I
    0.92
     Therefore
    0.90
    Activations Density 0.018%

    No Known Activations