© 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. 1032
    Prev
    Next
    INDEX
    Explanations

    brushing or brushing over

    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
    ve
    -2.58
    l
    -2.42
    ou
    -2.31
    u
    -2.22
    泐
    -2.20
    ܜ
    -2.19
    la
    -2.17
    lo
    -2.09
    跟
    -2.09
    ay
    -2.08
    POSITIVE LOGITS
     the
    2.31
     весна
    2.20
    %;
    2.13
    硤
    2.11
     verheir
    2.06
    bater
    2.03
    ˸
    2.00
     restaurantes
    1.99
     kräf
    1.98
    笫
    1.92
    Activations Density 0.007%

    No Known Activations