© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 105988
    Prev
    Next
    INDEX
    Explanations

    operations or selections

    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
     there
    -1.68
    selbe
    -1.34
    "),
    
    -1.32
     between
    -1.30
     scatola
    -1.25
     by
    -1.24
     cerimonia
    -1.22
     representado
    -1.22
     réduit
    -1.22
     time
    -1.22
    POSITIVE LOGITS
     olmak
    1.44
    ;
    1.33
     活動
    1.20
     usb
    1.19
     alebo
    1.18
    rogène
    1.16
    apropri
    1.14
    tainable
    1.13
     veya
    1.13
     ارائه
    1.10
    Activations Density 0.013%

    No Known Activations