© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11427
    Prev
    Next
    INDEX
    Explanations

    foreign language words

    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
     aren
    -0.86
     Ее
    -0.86
     in
    -0.83
     ✨
    -0.83
     possível
    -0.81
    ваем
    -0.80
     

    -0.80
    PHYSICS
    -0.80
     světa
    -0.79
     kated
    -0.77
    POSITIVE LOGITS
     imidlertid
    1.00
     Werkzeug
    0.98
     miglior
    0.95
    [])
    0.93
     soldadura
    0.92
     engran
    0.92
     Übungen
    0.92
     aggiorn
    0.91
     vandens
    0.91
    Nå
    0.90
    Activations Density 0.002%

    No Known Activations