© 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. 119784
    Prev
    Next
    INDEX
    Explanations

    hexagonal networks, Gloucester County

    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
    i
    -4.63
    ي
    -3.58
    -3.28
    其妙
    -3.27
    い
    -3.13
    ers
    -3.05
    真的很
    -2.95
    н
    -2.86
     Which
    -2.78
     {
    -2.73
    POSITIVE LOGITS
    灩
    3.06
    lossians
    2.91
    鈣
    2.75
    阗
    2.73
    肫
    2.69
    眈
    2.48
    接下来的
    2.45
    };*/
    2.41
     againſt
    2.39
     koska
    2.38
    Activations Density 0.088%

    No Known Activations