© 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. 59158
    Prev
    Next
    INDEX
    Explanations

    map tiles zoom

    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
     furniture
    -0.82
    RIST
    -0.76
     franquicia
    -0.74
     shape
    -0.73
    Courage
    -0.72
    欧盟
    -0.72
     courage
    -0.72
     staff
    -0.71
     hears
    -0.71
     apostar
    -0.71
    POSITIVE LOGITS
     tile
    1.32
    tile
    1.25
    Tile
    1.21
     zoom
    1.20
     TILE
    1.20
     Tile
    1.13
    zoom
    1.12
     tiles
    1.07
    Zoom
    1.02
     merc
    1.01
    Activations Density 0.014%

    No Known Activations