© 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. 9053
    Prev
    Next
    INDEX
    Explanations

    skiing and related context

    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
     –
    -3.50
     \
    -2.56
    一方で
    -2.45
     him
    -2.45
    但是在
    -2.34
    ↵↵↵↵↵↵↵↵↵↵
    -2.30
    怎么可能
    -2.22
    聼
    -2.20
     you
    -2.19
     —
    -2.16
    POSITIVE LOGITS
    蹰
    2.72
     faſt
    2.64
     Дне
    2.63
    英语
    2.50
     tunik
    2.48
     These
    2.42
    鉭
    2.42
    旆
    2.41
    锃
    2.41
     内衣
    2.38
    Activations Density 0.006%

    No Known Activations