© 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. 12033
    Prev
    Next
    INDEX
    Explanations

    numbers and calculations

    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
     miſ
    -2.02
     Inſ
    -2.02
     abſ
    -2.02
    킁
    -1.99
     viſ
    -1.97
    ཌ
    -1.95
     inſ
    -1.95
     tranſ
    -1.92
     Conſ
    -1.91
    栊
    -1.90
    POSITIVE LOGITS
     in
    3.08
     with
    2.41
     for
    2.33
     as
    2.31
     under
    2.17
     at
    2.11
     because
    2.09
     during
    2.00
    in
    2.00
     after
    1.98
    Activations Density 0.013%

    No Known Activations