© 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. 22-GEMMASCOPE-RES-131K
    7. 74908
    Prev
    Next
    INDEX
    Explanations

    computing services and topics

    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_22/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
    ,
    -1.10
    EXAMPLE
    -1.06
     such
    -1.05
     staff
    -1.02
     example
    -1.02
     television
    -1.01
     нарушения
    -1.01
     practicality
    -1.01
    ürme
    -1.00
     concern
    -0.97
    POSITIVE LOGITS
    τικού
    1.34
     réjou
    1.18
     katk
    1.16
     diriger
    1.13
    дный
    1.09
    Или
    1.09
     豆腐
    1.05
    tiendo
    1.05
     lämp
    1.05
    或是
    1.03
    Activations Density 0.013%

    No Known Activations