© 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. 42092
    Prev
    Next
    INDEX
    Explanations

    linking lists and numerical parameters

    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
     Both
    -2.44
     There
    -2.38
    {
    -2.33
     When
    -2.25
    after
    -2.23
     That
    -2.20
    Both
    -2.19
     Before
    -2.17
     Also
    -2.17
     For
    -2.17
    POSITIVE LOGITS
    蟶
    2.09
     protože
    2.06
     Inſ
    2.05
    趿
    2.03
    izedBox
    1.95
    tagHelper
    1.95
    
    1.93
    
    1.92
    KJV
    1.92
     carcasa
    1.92
    Activations Density 0.029%

    No Known Activations