© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1415
    Prev
    Next
    INDEX
    Explanations

    Q: and A: structure

    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
     wishful
    -0.87
     bewilder
    -0.87
     baffled
    -0.86
    леге
    -0.84
     praktischen
    -0.84
     giddy
    -0.82
    RECIPE
    -0.81
     DPM
    -0.81
    Ә
    -0.79
     doloroso
    -0.79
    POSITIVE LOGITS
    january
    0.92
     Customer
    0.91
     Verizon
    0.88
     Customers
    0.84
     Prime
    0.83
    cuba
    0.83
    ongyang
    0.81
     Tropical
    0.81
    节奏
    0.81
     Espagne
    0.81
    Activations Density 0.038%

    No Known Activations