© 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. 105628
    Prev
    Next
    INDEX
    Explanations

    delta

    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
    
    -2.75
     generando
    -2.66
     creando
    -2.58
     tohoto
    -2.50
     nadru
    -2.42
     They
    -2.41
    ↵↵
    -2.38
     pueda
    -2.34
     representan
    -2.34
     materiál
    -2.33
    POSITIVE LOGITS
    ╿
    3.00
     know
    2.75
    佧
    2.73
    
    2.64
    Most
    2.53
    Ⲉ
    2.50
    七月
    2.47
    餉
    2.45
    䉴
    2.42
    橚
    2.42
    Activations Density 0.006%

    No Known Activations