© 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. 22-GEMMASCOPE-RES-131K
    7. 71405
    Prev
    Next
    INDEX
    Explanations

    case numbers and DOIs

    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_22/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
    trails
    -1.09
     of
    -0.89
     on
    -0.88
    امة
    -0.87
    لالة
    -0.83
     hoga
    -0.82
    melons
    -0.79
     favourable
    -0.77
     mencionar
    -0.76
     one
    -0.74
    POSITIVE LOGITS
     submitted
    1.16
    elten
    1.11
    وقتی
    0.99
    Ї
    0.98
    教程
    0.98
    Размеры
    0.97
    ाइट
    0.96
    ajoz
    0.96
    danh
    0.94
     zeigten
    0.94
    Activations Density 0.145%

    No Known Activations