© 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. 38627
    Prev
    Next
    INDEX
    Explanations

    Chronic insomnia

    np_acts-logits-general · gemini-2.5-flash-lite

    XML or markup language code structures.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    曙
    -0.85
     ago
    -0.79
    famous
    -0.79
    springer
    -0.77
     Großbritannien
    -0.75
    seasonal
    -0.75
     kämpfen
    -0.75
     DBNull
    -0.74
    cancelled
    -0.74
     Xbox
    -0.74
    POSITIVE LOGITS
     اید
    0.82
    イント
    0.81
    コレ
    0.80
     erwäh
    0.79
    icon
    0.78
    impinan
    0.78
    どう
    0.77
    自ら
    0.74
    来找
    0.71
     icon
    0.70
    Activations Density 0.001%

    No Known Activations