© 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. 22-GEMMASCOPE-RES-131K
    7. 66654
    Prev
    Next
    INDEX
    Explanations

    Russian place names and languages

    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_22/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
    KommentareTeilen
    -1.42
     now
    -1.37
     your
    -1.18
    Bisous
    -1.16
     a
    -1.14
     also
    -1.13
    mariage
    -1.13
    幸好
    -1.09
     tijdens
    -1.07
     sierpnia
    -1.06
    POSITIVE LOGITS
    我們
    1.20
     ricca
    1.16
    コメント
    1.12
    であった
    1.10
    什麼
    1.09
     eccell
    1.09
    Beberapa
    1.09
    許多
    1.09
    這個
    1.06
    Filmo
    1.05
    Activations Density 0.013%

    No Known Activations