© 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. 960
    Prev
    Next
    INDEX
    Explanations

    SVG path data elements

    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
    確かに
    -0.83
     Mère
    -0.81
     peau
    -0.81
    Madre
    -0.78
     ileg
    -0.74
    𝐙
    -0.73
     favoris
    -0.72
     aula
    -0.71
     redness
    -0.71
    TableAdapter
    -0.71
    POSITIVE LOGITS
     ثابت
    0.80
     pokra
    0.79
    മ
    0.79
     maintained
    0.78
     dezelfde
    0.77
    义
    0.76
     remained
    0.75
     stayed
    0.75
     its
    0.73
    >>>>
    0.73
    Activations Density 0.020%

    No Known Activations