© 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. 3780
    Prev
    Next
    INDEX
    Explanations

    preterist beliefs or tense

    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
     if
    -1.94
    
    -1.91
     for
    -1.91
    pontos
    -1.85
     encontrará
    -1.84
    ";
    -1.81
    髡
    -1.80
     sorprendente
    -1.79
    ႐
    -1.77
     encontrarás
    -1.77
    POSITIVE LOGITS
    </h4>
    2.05
    玊
    2.05
    さまで
    2.05
    嵎
    2.02
    Джерело
    2.02
    quelles
    2.00
    öpfer
    1.98
     whom
    1.95
     και
    1.93
    GEBUR
    1.93
    Activations Density 0.001%

    No Known Activations