© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58055
    Prev
    Next
    INDEX
    Explanations

    mazes and labyrinths

    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
    ckley
    -0.77
     Couch
    -0.71
    ᅠ
    -0.71
     Pelicans
    -0.70
     mortars
    -0.70
     gathered
    -0.70
    ève
    -0.69
    tplatz
    -0.69
     Poto
    -0.69
    actylus
    -0.69
    POSITIVE LOGITS
     maze
    3.63
     labyrinth
    3.14
    maze
    2.67
     Maze
    2.33
     laby
    2.19
    Maze
    2.19
     Labyrinth
    2.05
    迷
    1.82
    abyrinth
    1.71
     maize
    1.70
    Activations Density 0.030%

    No Known Activations