© 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. 1719
    Prev
    Next
    INDEX
    Explanations

    API request code and configuration

    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
    НОГО
    -1.24
     kontro
    -1.13
     crois
    -1.13
     POLIC
    -1.08
     CHAMPION
    -1.07
     levert
    -1.07
     CONSTITUTION
    -1.05
     everybody
    -1.04
     ajoutez
    -1.03
     VICTORIA
    -1.03
    POSITIVE LOGITS
     must
    1.23
    aneity
    1.21
    我又
    1.20
     last
    1.11
    #}
    1.09
     поставки
    1.08
     тысячи
    1.08
    caping
    1.07
     had
    1.07
     hakkında
    1.06
    Activations Density 0.038%

    No Known Activations