© 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. 39212
    Prev
    Next
    INDEX
    Explanations

    URLs and technical content

    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
     or
    -2.22
     These
    -2.19
     What
    -2.05
     While
    -1.98
     so
    -1.97
     while
    -1.95
     there
    -1.88
     Using
    -1.88
     This
    -1.88
     providing
    -1.73
    POSITIVE LOGITS
    autoreleasepool
    2.31
    𖤍
    2.14
    ↵
    2.14
    ,:
    2.09
     secluded
    2.06
     a
    2.00
    rsquo
    1.96
    ,.
    1.93
    ,,,
    1.92
    initializeApp
    1.89
    Activations Density 0.055%

    No Known Activations