© 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. 69263
    Prev
    Next
    INDEX
    Explanations

    case, instead, adults

    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
     hvordan
    -0.90
     consummation
    -0.90
     ebenso
    -0.89
     numerous
    -0.88
     through
    -0.86
     الآخر
    -0.85
     cryptography
    -0.85
     exigen
    -0.83
     considerably
    -0.82
     transpa
    -0.81
    POSITIVE LOGITS
    ditionally
    1.09
    1.08
     Producción
    1.07
     Tienes
    1.07
     Ubicación
    1.03
     Mejora
    1.02
     Propiedad
    0.97
     Añade
    0.95
     Hace
    0.95
     urbanos
    0.95
    Activations Density 0.033%

    No Known Activations