© 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. 40319
    Prev
    Next
    INDEX
    Explanations

    your career prospects

    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
     PROVIDE
    -1.27
    篆
    -1.27
     these
    -1.21
     two
    -1.16
     получают
    -1.16
    ⌃
    -1.08
    ־ה
    -1.08
    鄙
    -1.07
     становника
    -1.05
     läßt
    -1.04
    POSITIVE LOGITS
     you
    1.98
     your
    1.97
     byste
    1.67
     FAQs
    1.34
     ‌
    1.33
    あなたが
    1.31
     můžete
    1.28
    ὕ
    1.24
     вам
    1.23
    あなた
    1.23
    Activations Density 0.013%

    No Known Activations