© 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. 68672
    Prev
    Next
    INDEX
    Explanations

    method or function calls

    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
    extremely
    -1.22
     páss
    -1.14
    athered
    -1.14
     quoc
    -1.12
    })->
    -1.11
     levar
    -1.09
    creating
    -1.03
    
    -1.03
     suporte
    -1.02
     anhänger
    -1.02
    POSITIVE LOGITS
     it
    1.53
     this
    1.19
     by
    1.07
     tersebut
    1.02
    Ⓒ
    0.93
     you
    0.91
     это
    0.89
     preocupado
    0.88
     memutus
    0.87
     فبراير
    0.87
    Activations Density 0.009%

    No Known Activations