© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 73861
    Prev
    Next
    INDEX
    Explanations

    CSS height declarations

    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
     width
    -1.55
    WIDTH
    -1.46
     widths
    -1.43
     WIDTH
    -1.34
     wider
    -1.34
    宽度
    -1.34
     wide
    -1.28
     widening
    -1.27
     Width
    -1.27
     widened
    -1.23
    POSITIVE LOGITS
     height
    1.33
    height
    1.22
    Height
    0.89
     Height
    0.86
    高さ
    0.80
    胳膊
    0.75
    カテゴリ
    0.73
     fuc
    0.73
     Malang
    0.72
     Cx
    0.71
    Activations Density 0.031%

    No Known Activations