© 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. 41926
    Prev
    Next
    INDEX
    Explanations

    airtight and sealed

    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
    o
    -2.47
     him
    -1.73
     спустя
    -1.73
     Our
    -1.65
     Volkes
    -1.64
     resulta
    -1.62
    こだわ
    -1.62
    </td>
    -1.62
    崛起
    -1.62
    鸰
    -1.60
    POSITIVE LOGITS
    其妙
    2.22
    𝐬
    2.16
    INTENANCE
    1.73
     класс
    1.66
    چار
    1.65
    тории
    1.65
     فقط
    1.65
    踅
    1.64
    ANIA
    1.63
    erste
    1.62
    Activations Density 0.006%

    No Known Activations