© 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. 70184
    Prev
    Next
    INDEX
    Explanations

    mazda, maze, mazzuchelli, mazumdar

    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
     現貨
    -0.80
     Hoteles
    -0.77
    UBLE
    -0.75
    贵族
    -0.74
    뒤
    -0.73
    によると
    -0.73
    currentPosition
    -0.73
    izhou
    -0.72
    uble
    -0.70
    られています
    -0.70
    POSITIVE LOGITS
     Maz
    1.11
    Maz
    0.85
    мен
    0.85
     Maze
    0.81
     maz
    0.80
    𝑡
    0.77
    maze
    0.77
     stron
    0.72
    gas
    0.72
    亜
    0.71
    Activations Density 0.018%

    No Known Activations