© 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. 103948
    Prev
    Next
    INDEX
    Explanations

    maze Labyrinth

    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
    antia
    -0.79
    omitempty
    -0.79
     accumulation
    -0.78
     کال
    -0.77
    Serial
    -0.76
    <0xEF>
    -0.76
    PORARY
    -0.75
     нако
    -0.74
     сверху
    -0.74
     acum
    -0.72
    POSITIVE LOGITS
     Maze
    1.35
     maze
    1.09
    Maze
    1.08
    maze
    1.02
     Glad
    1.01
    WICK
    0.99
     Newt
    0.93
     Flare
    0.93
     glade
    0.89
     labyrinth
    0.81
    Activations Density 0.012%

    No Known Activations