© 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. 34-GEMMASCOPE-RES-131K
    7. 50421
    Prev
    Next
    INDEX
    Explanations

    evaluate expressions and activities

    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
    눅
    -0.82
    ゔ
    -0.78
    邁
    -0.75
    ďte
    -0.74
    гли
    -0.73
     поток
    -0.71
    jast
    -0.69
     Chom
    -0.69
    ytet
    -0.68
     انتخاب
    -0.68
    POSITIVE LOGITS
    getChildren
    0.91
    とろ
    0.77
    🔧
    0.76
    UNICIP
    0.75
    kubernetes
    0.74
    нін
    0.73
    pores
    0.72
    瘦
    0.71
     premiums
    0.71
     年度
    0.70
    Activations Density 0.016%

    No Known Activations