© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60646
    Prev
    Next
    INDEX
    Explanations

    ordinal number followed by Cir

    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
     other
    -1.66
     to
    -1.63
     in
    -1.59
     її
    -1.57
     '
    -1.54
     inspiradoras
    -1.53
     "+
    -1.52
     its
    -1.51
     március
    -1.45
    ().
    -1.43
    POSITIVE LOGITS
    料
    1.46
    퐼
    1.45
    鷽
    1.39
     NSCoder
    1.39
    ディオ
    1.36
    咲き
    1.35
    edificio
    1.34
     dogged
    1.33
     lỗ
    1.33
    jerg
    1.33
    Activations Density 0.087%

    No Known Activations