© 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. 20517
    Prev
    Next
    INDEX
    Explanations

    social and economic cooperation

    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
    ꗃ
    -1.20
     Đó
    -1.15
    ウィキ
    -1.13
     внутріш
    -1.10
    BeforeAll
    -1.10
     from
    -1.09
    🇾
    -1.08
     hacerle
    -1.06
    Перед
    -1.05
     Daarnaast
    -1.05
    POSITIVE LOGITS
     rather
    1.48
     other
    1.26
    公共
    1.24
     السياس
    1.21
     actuel
    1.20
    肱
    1.17
     siècle
    1.13
    が使
    1.11
     instead
    1.10
     others
    1.09
    Activations Density 0.070%

    No Known Activations