© 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. 67743
    Prev
    Next
    INDEX
    Explanations

    diagnostic and medical terms

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

    phrases that introduce specific details or examples in academic or informational text.

    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_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
     موقع
    -0.88
     opposite
    -0.82
    ypress
    -0.81
    letín
    -0.81
    全体
    -0.78
    uoto
    -0.78
    opposite
    -0.77
    ulsi
    -0.77
    beth
    -0.77
     PORTRAIT
    -0.77
    POSITIVE LOGITS
     mentioned
    1.39
     included
    1.09
     listed
    1.05
     indicated
    1.04
     identified
    1.02
     cited
    1.01
     each
    0.94
     further
    0.93
     referred
    0.90
    刚才
    0.86
    Activations Density 0.121%

    No Known Activations