© 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. 874
    Prev
    Next
    INDEX
    Explanations

    class keyword in code

    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
    錞
    -1.94
    Beberapa
    -1.89
    Menurut
    -1.79
    Kedua
    -1.74
    Kelebihan
    -1.73
    豨
    -1.73
    Meskipun
    -1.72
     other
    -1.70
    Ketika
    -1.70
    Sebagai
    -1.69
    POSITIVE LOGITS
     —
    1.75
     cuyos
    1.57
    MANY
    1.56
    椅子
    1.55
     gelernt
    1.53
    のも
    1.52
    peated
    1.51
    ことから
    1.50
     fashioned
    1.49
     wären
    1.49
    Activations Density 0.018%

    No Known Activations