© 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. 119502
    Prev
    Next
    INDEX
    Explanations

    intense unpleasantness

    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
     唯美
    -2.02
    卺
    -2.00
     苹果
    -1.98
    夲
    -1.93
    vänd
    -1.88
     mauva
    -1.88
    嫆
    -1.82
    ETIES
    -1.81
    🧞
    -1.81
    マイズ
    -1.75
    POSITIVE LOGITS
     it
    2.56
    ↵
    2.38
    1
    1.84
     
    1.80
    3
    1.55
     With
    1.51
    ŚĆ
    1.50
    .
    1.48
     .
    1.46
     amounts
    1.45
    Activations Density 0.015%

    No Known Activations