© 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. 84624
    Prev
    Next
    INDEX
    Explanations

    less fortunate, lucky, luckier

    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
     الفي
    -0.81
    ENTION
    -0.77
    webView
    -0.77
    ፍ
    -0.77
     exciting
    -0.77
    пат
    -0.76
    Exciting
    -0.75
    uction
    -0.75
     αυ
    -0.74
    elemField
    -0.74
    POSITIVE LOGITS
     lucky
    2.55
     fortunate
    1.98
     luck
    1.92
    lucky
    1.90
     Lucky
    1.77
    Lucky
    1.73
     LUCK
    1.49
    fortunate
    1.48
    LUCK
    1.39
    幸運
    1.34
    Activations Density 0.014%

    No Known Activations