© 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. 85269
    Prev
    Next
    INDEX
    Explanations

    relegation and demotion

    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
    itemBuilder
    -2.41
     }));
    -2.39
    摶
    -2.31
     }))
    -2.28
     帳
    -2.27
     户
    -2.25
    𝐨
    -2.20
    좇
    -2.20
    ｐ
    -2.20
     話
    -2.19
    POSITIVE LOGITS
    ↵
    5.50
    ’
    2.81
    ,”
    2.67
    ”
    2.58
     
    2.53
    淠
    2.45
    跸
    2.44
     идеально
    2.36
     небольшой
    2.30
    '
    2.28
    Activations Density 0.003%

    No Known Activations