© 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. 102908
    Prev
    Next
    INDEX
    Explanations

    food and community events

    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
    glMatrixMode
    -0.82
     теку
    -0.81
    caffe
    -0.80
    cetines
    -0.79
     revolt
    -0.76
    oray
    -0.76
     yoga
    -0.75
    쉽
    -0.75
    ху
    -0.75
    pair
    -0.74
    POSITIVE LOGITS
     meal
    1.13
     horseshoe
    1.05
     fundraiser
    1.00
    利润
    0.96
    メ
    0.94
     committee
    0.93
     meals
    0.91
     église
    0.91
     decora
    0.90
    Menu
    0.88
    Activations Density 0.028%

    No Known Activations