© 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. 10-GEMMASCOPE-RES-131K
    7. 87036
    Prev
    Next
    INDEX
    Explanations

    19th century

    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_10/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
     it
    -1.92
     vecin
    -1.70
     возь
    -1.64
     OUTER
    -1.61
     if
    -1.57
     by
    -1.55
     Assays
    -1.54
    (^_^
    -1.54
    靫
    -1.52
     Therapies
    -1.51
    POSITIVE LOGITS
     years
    1.95
     Top
    1.93
    鹮
    1.80
    lassification
    1.77
     I
    1.68
    乆
    1.68
     period
    1.67
     last
    1.67
    </sup>
    1.66
    </em>
    1.63
    Activations Density 0.140%

    No Known Activations