© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 25679
    Prev
    Next
    INDEX
    Explanations

    Rangers show, Q:

    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
    getJSONObject
    -0.85
     Transc
    -0.83
    Ў
    -0.81
     paraf
    -0.79
     Infór
    -0.79
    整数
    -0.79
    LabelTagHelper
    -0.77
     Fairly
    -0.76
     ブラウス
    -0.76
    ({
    
    -0.76
    POSITIVE LOGITS
    一方面
    0.87
    閨
    0.86
     Karl
    0.84
    إنه
    0.83
    ytick
    0.81
     sabias
    0.81
     recarg
    0.80
     البلاد
    0.80
     членов
    0.79
     నీ
    0.79
    Activations Density 0.000%

    No Known Activations