© 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. 124575
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and commands

    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
    哢
    -2.19
    是什么意思
    -1.93
    是怎么
    -1.87
    豨
    -1.80
    是我们
    -1.73
     our
    -1.72
    结语
    -1.70
    portraits
    -1.69
     concorda
    -1.68
    jaqueta
    -1.67
    POSITIVE LOGITS
    "
    2.20
    en
    1.96
    I
    1.88
    he
    1.81
     i
    1.73
    ti
    1.59
    桖
    1.58
     OF
    1.57
    另外
    1.55
     nehmen
    1.55
    Activations Density 0.012%

    No Known Activations