© 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. 22-GEMMASCOPE-RES-131K
    7. 104354
    Prev
    Next
    INDEX
    Explanations

    programming language syntax

    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_22/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
    ּוֹ
    -2.78
    ַּ
    -2.16
    ִּ
    -2.13
    ְּ
    -1.93
    וּ
    -1.78
    ֶּ
    -1.72
    ֵּ
    -1.57
     اندروید
    -1.52
    וּ
    -1.51
     السياس
    -1.50
    POSITIVE LOGITS
    ׇ
    2.03
     блюдо
    1.66
     katholischen
    1.41
    ֺ
    1.39
    ﷲ
    1.38
    ﻷ
    1.34
     τὰ
    1.30
     النبات
    1.28
     Erkrank
    1.27
     الجلد
    1.26
    Activations Density 0.018%

    No Known Activations