© 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. 287
    Prev
    Next
    INDEX
    Explanations

    names starting with Kir

    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
    呖
    -4.13
    晳
    -2.73
    ！！！！！
    -2.66
     metre
    -2.64
    
    -2.53
    ဴ
    -2.52
     of
    -2.48
    鱨
    -2.48
    吖
    -2.47
    囀
    -2.47
    POSITIVE LOGITS
    1
    3.34
    [
    3.19
    .
    2.95
    ные
    2.81
     `
    2.78
    9
    2.64
    8
    2.59
    3
    2.58
    }
    2.50
    n
    2.47
    Activations Density 0.003%

    No Known Activations