© 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. 86992
    Prev
    Next
    INDEX
    Explanations

    visitors with, you every, users by, selectors after

    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
    んでも
    -1.20
     tutaj
    -1.02
     to
    -1.02
     чтобы
    -0.99
    toObject
    -0.95
     soprav
    -0.94
    ']).
    -0.94
     щоб
    -0.92
     بشر
    -0.90
    ियन
    -0.88
    POSITIVE LOGITS
     with
    3.73
     своими
    2.17
     by
    2.05
    ด้วย
    1.97
     своим
    1.96
     svým
    1.84
     своей
    1.80
     swoim
    1.60
     through
    1.59
     due
    1.46
    Activations Density 0.056%

    No Known Activations