© 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. 991
    Prev
    Next
    INDEX
    Explanations

    tokens after programming constructs

    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
    </h2>
    -1.63
     
    -1.60
    賑
    -1.52
     &
    -1.45
    </strong>
    -1.41
    气氛
    -1.41
    phile
    -1.38
    ……”
    -1.36
     निम्
    -1.36
    那位
    -1.32
    POSITIVE LOGITS
     honnête
    1.60
    cestry
    1.55
    ية
    1.43
    doğan
    1.42
     完了
    1.42
     Église
    1.38
    我們
    1.36
     compréhen
    1.34
     antworten
    1.34
     FontWeight
    1.34
    Activations Density 0.006%

    No Known Activations