© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 59296
    Prev
    Next
    INDEX
    Explanations

    database connection drivers

    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
     Clarissa
    -0.83
    noe
    -0.79
     systemu
    -0.76
    ḡ
    -0.76
    ยม
    -0.75
     Reserv
    -0.75
     goat
    -0.75
    WebGL
    -0.74
     buildings
    -0.72
    模特
    -0.72
    POSITIVE LOGITS
     driver
    1.67
     Driver
    1.46
    driver
    1.41
     Drivers
    1.37
     drivers
    1.36
    Driver
    1.34
     JDBC
    1.19
    Drivers
    1.13
    ドライバー
    1.09
    drivers
    1.04
    Activations Density 0.160%

    No Known Activations