© 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. 98480
    Prev
    Next
    INDEX
    Explanations

    NS CollectionView, type UncallableFunction, Mod ulatory, Daniel Garodnick

    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
     velkommen
    -1.13
     manzana
    -1.09
    
    -1.08
     dianteira
    -1.06
     escudo
    -1.06
     seus
    -1.03
    нија
    -1.03
    楫
    -1.02
     Gewalt
    -1.02
     их
    -1.02
    POSITIVE LOGITS
     such
    1.26
     чаще
    1.05
     astfel
    1.03
     sostiene
    1.00
     näh
    1.00
    ôs
    0.97
    atoes
    0.96
     the
    0.94
     unterstüt
    0.93
    шений
    0.93
    Activations Density 0.000%

    No Known Activations