© 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. 34-GEMMASCOPE-RES-131K
    7. 34623
    Prev
    Next
    INDEX
    Explanations

    public class startup/component configuration

    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_34/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
     Đó
    -0.84
    opcion
    -0.78
    不如
    -0.77
    visite
    -0.76
    Hindi
    -0.75
    Hons
    -0.75
     monoclonal
    -0.73
    Britney
    -0.73
    OOTD
    -0.73
     Drexel
    -0.73
    POSITIVE LOGITS
     configure
    0.98
     configura
    0.93
     Configure
    0.89
    ạt
    0.87
    Configure
    0.86
    config
    0.85
    Setup
    0.85
     konfigura
    0.83
    remadura
    0.82
     configuration
    0.81
    Activations Density 0.030%

    No Known Activations