© 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. 105832
    Prev
    Next
    INDEX
    Explanations

    St. Louis

    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
    n
    -2.92
    t
    -2.89
    d
    -2.58
    a
    -2.19
    to
    -2.08
    </h4>
    -2.06
    ("
    -2.00
    with
    -1.97
    4
    -1.95
    全都
    -1.86
    POSITIVE LOGITS
    ㍑
    2.08
    ","#
    2.03
    "){
    1.96
    窨
    1.95
    ㈥
    1.93
    葙
    1.90
    ")]
    1.87
     {
    1.87
    
    1.87
    ᅫ
    1.86
    Activations Density 0.007%

    No Known Activations