© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 70398
    Prev
    Next
    INDEX
    Explanations

    UC abbreviations and acronyms

    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
    '
    -2.59
    ),
    -2.42
    鬭
    -2.39
    砹
    -2.31
     имеются
    -2.28
    觧
    -2.28
    hasilkan
    -2.27
     jesus
    -2.27
    yarakat
    -2.23
    毉
    -2.23
    POSITIVE LOGITS
     embrace
    2.56
    ܜ
    2.44
     desapare
    2.41
     glit
    2.38
     estimate
    2.34
     avem
    2.33
                    
    2.27
    新款
    2.25
     putem
    2.22
     offer
    2.20
    Activations Density 0.004%

    No Known Activations