© 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. 123738
    Prev
    Next
    INDEX
    Explanations

    the name Miller

    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
    ’
    -4.06
    ↵
    -3.86
    n
    -2.83
    ↵↵
    -2.80
    真的很
    -2.69
    The
    -2.64
    还没
    -2.59
    真的是
    -2.52
    end
    -2.50
    ating
    -2.48
    POSITIVE LOGITS
    驺
    2.94
    琑
    2.94
    郿
    2.81
    𖤣
    2.66
    
    2.63
    嫫
    2.56
    Ꮀ
    2.53
     refugi
    2.48
    釭
    2.47
    蚨
    2.47
    Activations Density 0.003%

    No Known Activations