© 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. 25710
    Prev
    Next
    INDEX
    Explanations

    code statements or file headers

    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
    ILS
    -0.79
    ODI
    -0.79
    gering
    -0.75
    ynos
    -0.75
    ються
    -0.74
    chinen
    -0.74
     вкусу
    -0.73
    IARC
    -0.71
     doğru
    -0.71
     ī
    -0.71
    POSITIVE LOGITS
    ellar
    0.71
     сок
    0.69
     memb
    0.69
    actus
    0.68
     Antiques
    0.68
     Yag
    0.67
     Pease
    0.66
     operar
    0.66
     attempting
    0.65
     порядок
    0.64
    Activations Density 0.030%

    No Known Activations