© 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. 73369
    Prev
    Next
    INDEX
    Explanations

    Rare times, IgE, Febrile

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

    HTML/XML markup and code formatting patterns in structured documents.

    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
     古着
    -0.92
     görü
    -0.90
    _;
    -0.90
     oorlog
    -0.88
    膊
    -0.87
    
    -0.85
    ilyen
    -0.85
     AGENCIES
    -0.85
    _'.$
    -0.84
    𝟕
    -0.84
    POSITIVE LOGITS
    صاص
    0.83
    どう
    0.82
    نع
    0.81
     another
    0.75
    ztes
    0.75
    我們
    0.74
     easier
    0.74
     lopp
    0.74
    0.74
     everywhere
    0.73
    Activations Density 0.005%

    No Known Activations