© 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. 11971
    Prev
    Next
    INDEX
    Explanations

    death penalty, stay execution

    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
    
    -1.73
     In
    -1.42
    </h3>
    -1.41
     pojawia
    -1.37
     bestow
    -1.37
     increased
    -1.31
    0
    -1.31
    raisals
    -1.30
    raught
    -1.30
     遇
    -1.27
    POSITIVE LOGITS
    这就是
    1.63
    比如说
    1.57
    ;
    1.53
     muerta
    1.52
    关于
    1.48
    内容
    1.47
     don
    1.47
    ――
    1.44
     illa
    1.42
    Agosto
    1.41
    Activations Density 0.010%

    No Known Activations