© 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. 6935
    Prev
    Next
    INDEX
    Explanations

    school board or district

    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
     PID
    -0.91
    keydown
    -0.78
     troopers
    -0.77
    雑
    -0.74
    IMAS
    -0.73
    Rider
    -0.73
    適合
    -0.70
     PUC
    -0.70
    營業時間
    -0.69
     ERR
    -0.69
    POSITIVE LOGITS
     board
    1.16
    Board
    1.02
     Board
    1.02
     district
    0.91
     BOARD
    0.89
    board
    0.85
    District
    0.84
    chool
    0.84
     gute
    0.84
     District
    0.79
    Activations Density 0.032%

    No Known Activations