© 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. 9355
    Prev
    Next
    INDEX
    Explanations

    acronyms and proper nouns

    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
    庒
    -3.25
    衚
    -3.16
    鹟
    -2.98
    숱
    -2.97
     congreso
    -2.95
     interessantes
    -2.91
     手绘
    -2.88
    ﻚ
    -2.83
     Prancis
    -2.83
     丁目
    -2.83
    POSITIVE LOGITS
    re
    2.98
    isation
    2.83
    </i>
    2.73
     apenas
    2.66
    м
    2.56
    il
    2.55
     i
    2.48
     [
    2.48
     we
    2.47
    (
    2.47
    Activations Density 0.023%

    No Known Activations