© 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. 22-GEMMASCOPE-RES-131K
    7. 98183
    Prev
    Next
    INDEX
    Explanations

    change, football, business, making, songwriting, delivery, computing, data, development, win

    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_22/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
     یا
    -1.20
     of
    -1.13
     или
    -1.12
     its
    -1.09
     to
    -1.05
    或
    -1.04
     zeven
    -0.98
     espere
    -0.98
    rdoba
    -0.97
    难怪
    -0.97
    POSITIVE LOGITS
    Юлия
    1.24
    
    1.23
     Hacer
    1.19
     dialysis
    1.13
    ží
    1.13
     ขนาด
    1.13
    Կ
    1.10
     Porque
    1.09
    níci
    1.08
     Debido
    1.07
    Activations Density 0.078%

    No Known Activations