© 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. 34-GEMMASCOPE-RES-131K
    7. 1717
    Prev
    Next
    INDEX
    Explanations

    Thursdays, dates, times

    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
     without
    -1.03
     nearly
    -1.00
     so
    -1.00
     because
    -0.99
     more
    -0.96
     just
    -0.96
     seeking
    -0.95
     although
    -0.94
     seemingly
    -0.93
     phenomenal
    -0.93
    POSITIVE LOGITS
     คา
    1.05
    possibly
    0.98
    directly
    0.94
    蓠
    0.94
     Bronco
    0.94
    potentially
    0.93
    inerary
    0.91
     แปล
    0.90
    autoreleasepool
    0.90
    uib
    0.90
    Activations Density 0.011%

    No Known Activations