© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 65972
    Prev
    Next
    INDEX
    Explanations

    control group

    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
    穑
    -1.56
    カッコいい
    -1.49
    ܆
    -1.47
    我知道
    -1.44
    釭
    -1.40
     his
    -1.38
    UrlEncoded
    -1.36
    了个
    -1.36
     pretože
    -1.35
    MessageWindow
    -1.33
    POSITIVE LOGITS
    cestor
    1.73
    Ако
    1.69
    čení
    1.65
     никогда
    1.60
    ()=>{
    1.59
    Один
    1.54
     วาด
    1.48
    
    1.46
     nigdy
    1.46
    erintah
    1.46
    Activations Density 0.093%

    No Known Activations