© 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. 34-GEMMASCOPE-RES-131K
    7. 93683
    Prev
    Next
    INDEX
    Explanations

    initialization and setup

    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_34/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
     définiti
    -0.84
     bekas
    -0.84
     kisah
    -0.80
     čer
    -0.78
    archiwizowane
    -0.76
     actuels
    -0.75
     portato
    -0.75
     aggiunto
    -0.75
     praktik
    -0.74
     กล่อง
    -0.74
    POSITIVE LOGITS
     initialization
    4.63
     init
    4.47
    初始化
    4.47
     initialize
    4.47
    init
    4.13
    Init
    3.88
    initialize
    3.80
     Init
    3.78
     Initialize
    3.69
     初始化
    3.66
    Activations Density 0.178%

    No Known Activations