© 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. 53828
    Prev
    Next
    INDEX
    Explanations

    apparatus and devices

    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
    veyard
    -0.88
    ptions
    -0.84
    に行った
    -0.84
    ようになる
    -0.77
    ورات
    -0.76
    Madeleine
    -0.75
     gesagt
    -0.75
     acheter
    -0.75
     продуктов
    -0.74
    戦略
    -0.73
    POSITIVE LOGITS
     device
    2.48
     devices
    2.06
     apparatus
    1.96
    device
    1.86
     mechanism
    1.78
    DEVICE
    1.63
    Device
    1.58
    getDevice
    1.58
     Device
    1.58
     arrangement
    1.56
    Activations Density 1.053%

    No Known Activations