© 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. 64521
    Prev
    Next
    INDEX
    Explanations

    domain/source names and questions

    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
    AVG
    -0.73
     Instead
    -0.71
    ruptive
    -0.70
     عز
    -0.69
    vagrant
    -0.68
     kerana
    -0.68
    אז
    -0.68
     Bellow
    -0.67
    nursing
    -0.67
    Instead
    -0.67
    POSITIVE LOGITS
     Yandex
    1.08
     clk
    0.82
     teaming
    0.78
     GestureDetector
    0.77
     tame
    0.76
     diva
    0.75
     Eats
    0.75
     Yankee
    0.75
    大根
    0.75
     εκεί
    0.74
    Activations Density 0.010%

    No Known Activations