© 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. 45604
    Prev
    Next
    INDEX
    Explanations

    method setup and initialization

    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
    cardigan
    -0.92
     tertulis
    -0.92
     innehåller
    -0.91
    Nå
    -0.86
     咖
    -0.82
     squats
    -0.82
     todella
    -0.81
    akhstan
    -0.81
     Coatings
    -0.80
    verhältnis
    -0.80
    POSITIVE LOGITS
    initView
    1.21
     init
    1.16
     listeners
    1.05
     views
    1.00
     set
    0.96
    Views
    0.94
     initial
    0.93
     composants
    0.92
     data
    0.91
    initial
    0.90
    Activations Density 0.004%

    No Known Activations