© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11182
    Prev
    Next
    INDEX
    Explanations

    email addresses and parentheses

    np_acts-logits-general · gemini-2.5-flash-lite

    arithmetic operations and results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     routinely
    0.42
    
    0.42
     برخی
    0.41
     certamente
    0.41
    これまで
    0.41
    architecture
    0.39
    develop
    0.39
    developing
    0.39
    
    0.39
    
    0.38
    POSITIVE LOGITS
     idk
    0.87
     plz
    0.71
    ➕
    0.70
     उसमे
    0.69
     이거
    0.67
     seperate
    0.66
     đc
    0.66
    してる
    0.65
     karna
    0.64
    됬
    0.64
    Activations Density 0.150%

    No Known Activations