© 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. 53993
    Prev
    Next
    INDEX
    Explanations

    introduces a topic or question

    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
     saveurs
    -1.42
    יך
    -1.38
    ungkap
    -1.34
     शुर
    -1.32
     komment
    -1.31
    küche
    -1.30
     évé
    -1.29
     árbitro
    -1.27
     kommunik
    -1.27
     czerwony
    -1.26
    POSITIVE LOGITS
     then
    1.63
     its
    1.33
     sturdy
    1.27
     ouvido
    1.17
    皈
    1.16
    叽
    1.15
     damals
    1.13
     beloved
    1.10
    |
    1.08
     magnificent
    1.05
    Activations Density 0.009%

    No Known Activations