© 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. 10-GEMMASCOPE-RES-131K
    7. 1227
    Prev
    Next
    INDEX
    Explanations

    CIA spy operations

    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_10/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
    '
    -2.63
     )
    -2.44
    遹
    -2.41
    訁
    -2.31
    彀
    -2.22
    荅
    -2.17
     подготовка
    -2.16
     erbjud
    -2.16
     categorized
    -2.16
     esencia
    -2.13
    POSITIVE LOGITS
    at
    2.83
    <
    2.59
    {
    2.14
    鱚
    2.14
     étages
    2.09
    up
    2.06
    🌻
    2.03
    geſ
    2.03
     في
    1.95
    戈
    1.94
    Activations Density 0.003%

    No Known Activations