© 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. 10-GEMMASCOPE-RES-131K
    7. 21796
    Prev
    Next
    INDEX
    Explanations

    Protestant church and reformation

    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
    因为他
    -2.50
     "
    -2.19
     naturales
    -2.11
     primeira
    -2.09
    說是
    -1.95
    闡
    -1.92
    あげて
    -1.91
    待って
    -1.91
    他說
    -1.90
    是这样的
    -1.88
    POSITIVE LOGITS
    
    2.42
    :”
    2.41
    ꒥
    2.25
    ⤙
    2.08
    “,
    2.02
     gearbeitet
    2.02
    “.
    1.99
    ”,
    1.99
    厖
    1.98
    骓
    1.97
    Activations Density 0.002%

    No Known Activations