© 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. 110708
    Prev
    Next
    INDEX
    Explanations

    bu name parts

    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
    复制代码
    -0.74
     studies
    -0.72
    Purchasing
    -0.71
     purchases
    -0.70
    Better
    -0.69
     ALIGN
    -0.69
    hluk
    -0.69
    问道
    -0.68
     Similar
    -0.68
     maggiori
    -0.68
    POSITIVE LOGITS
    ிய
    0.77
    vær
    0.76
     Learners
    0.73
     sonra
    0.70
     Aliens
    0.70
    🏌
    0.69
     Summaries
    0.69
    fering
    0.69
    Vega
    0.69
     stint
    0.68
    Activations Density 0.031%

    No Known Activations