© 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. 34-GEMMASCOPE-RES-131K
    7. 1950
    Prev
    Next
    INDEX
    Explanations

    Korean context and news

    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_34/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
    TQ
    -0.76
     .....
    -0.75
    hu
    -0.75
     should
    -0.74
     foly
    -0.72
     ....
    -0.72
    !!
    -0.71
     }^{*
    -0.68
     iconst
    -0.68
     pero
    -0.66
    POSITIVE LOGITS
    歌手
    0.84
    
    0.83
     procra
    0.83
     SMALL
    0.82
     SOUTH
    0.81
    黑衣
    0.81
     jsi
    0.79
    ectos
    0.79
    heiser
    0.79
    Lø
    0.79
    Activations Density 0.003%

    No Known Activations