© 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. 102833
    Prev
    Next
    INDEX
    Explanations

    writing contests and programs

    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
    ’
    -1.45
    …’
    -1.12
    {
    -1.09
     sog
    -0.98
    ,”
    -0.98
    تیجه
    -0.96
    Designed
    -0.95
    ,’
    -0.93
    无数
    -0.92
    O
    -0.92
    POSITIVE LOGITS
     Writing
    1.34
    ✍
    1.15
     写
    1.14
    Writing
    1.09
     писать
    1.06
    ▝
    1.05
    ⛦
    1.04
     Vä
    1.02
    ナブル
    1.02
     about
    1.00
    Activations Density 0.031%

    No Known Activations