© 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. 3682
    Prev
    Next
    INDEX
    Explanations

    harvesting and subsequent actions

    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
    el
    -2.52
    『
    -2.41
    ר
    -2.22
    il
    -2.14
    
    -2.11
    .";
    -2.02
    lo
    -2.02
    8
    -1.97
    en
    -1.96
    ti
    -1.94
    POSITIVE LOGITS
    典型的
    2.28
     maravillosa
    2.03
    鬨
    1.95
    
    1.94
    ︲
    1.93
    愎
    1.91
    鲻
    1.90
     junger
    1.87
    
    1.86
    firmasi
    1.85
    Activations Density 0.009%

    No Known Activations