© 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. 55773
    Prev
    Next
    INDEX
    Explanations

    grid and layout containers

    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
    zani
    -0.74
     ớt
    -0.74
    視野
    -0.73
    ਆ
    -0.71
    示意图
    -0.71
    HeaderComponent
    -0.70
    帛
    -0.68
     θα
    -0.68
    ıdır
    -0.67
    AutoModerator
    -0.67
    POSITIVE LOGITS
     Grid
    1.89
     grid
    1.81
    Grid
    1.78
    grid
    1.71
    GRID
    1.34
     grids
    1.30
     GRID
    1.27
    Card
    1.26
    card
    1.17
     Card
    1.15
    Activations Density 0.152%

    No Known Activations