© 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. 3823
    Prev
    Next
    INDEX
    Explanations

    contractor roles

    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
    {
    -2.83
    裡的
    -2.77
     feine
    -2.72
     grüne
    -2.41
    西班牙
    -2.27
     offene
    -2.19
    籥
    -2.19
     übri
    -2.19
     крупные
    -2.19
     weiße
    -2.17
    POSITIVE LOGITS
    酲
    3.42
    亊
    2.91
    岨
    2.78
    ᚺ
    2.70
    ᠁
    2.66
     スープ
    2.64
    洐
    2.59
    鵄
    2.56
    觏
    2.53
    祼
    2.47
    Activations Density 0.003%

    No Known Activations