© 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. 81045
    Prev
    Next
    INDEX
    Explanations

    intersection or junction

    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
    welling
    -0.79
    printLine
    -0.76
    >
    -0.74
     tablette
    -0.73
     kanak
    -0.71
    linie
    -0.71
     velho
    -0.70
    fragments
    -0.70
     terap
    -0.69
    巻
    -0.69
    POSITIVE LOGITS
     intersection
    4.53
     intersections
    4.09
    intersection
    3.48
     Intersection
    3.30
    Intersection
    3.23
     junction
    3.02
     junctions
    2.66
     roundabout
    2.64
     intersect
    2.55
     crossroads
    2.38
    Activations Density 0.054%

    No Known Activations