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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107119
    Prev
    Next
    INDEX
    Explanations

    singleton design pattern

    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
    ContentAlignment
    -0.94
    tissa
    -0.87
     moindre
    -0.84
     piden
    -0.83
     thérape
    -0.82
    ota
    -0.82
    ziesz
    -0.80
     Serbie
    -0.80
     arrêté
    -0.80
     cél
    -0.79
    POSITIVE LOGITS
     singleton
    2.78
     Singleton
    2.73
    Singleton
    2.64
    singleton
    2.47
     getInstance
    2.11
    getInstance
    1.89
    SINGLE
    1.70
     SINGLE
    1.65
     instance
    1.64
     singlet
    1.64
    Activations Density 0.042%

    No Known Activations