© 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. 54549
    Prev
    Next
    INDEX
    Explanations

    insurance and accident

    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
     europea
    -1.32
    象徴
    -1.26
     zoll
    -1.23
     segredo
    -1.16
    去找
    -1.13
     voltar
    -1.13
     effectué
    -1.10
     portavoz
    -1.09
    графия
    -1.09
     sofrer
    -1.09
    POSITIVE LOGITS
    :'#
    1.38
     bordados
    1.37
    RefreshLayout
    1.33
     Países
    1.29
    棹
    1.27
    :{
    1.27
     oídos
    1.26
     Boletín
    1.21
    ólico
    1.17
    ？』
    1.17
    Activations Density 0.316%

    No Known Activations