© 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. 102565
    Prev
    Next
    INDEX
    Explanations

    economic survey or working paper

    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
     feveral
    -0.75
    去掉
    -0.72
    чений
    -0.71
    佥
    -0.71
    uomo
    -0.71
    团体
    -0.71
    enseignements
    -0.70
     nilai
    -0.70
     رفته
    -0.69
    <0xA8>
    -0.69
    POSITIVE LOGITS
     working
    2.19
     Working
    1.99
    Working
    1.80
     paper
    1.59
    working
    1.57
    WORKING
    1.57
     Discussion
    1.47
     WORKING
    1.45
     papers
    1.42
    DISCUSSION
    1.39
    Activations Density 0.028%

    No Known Activations