© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3489
    Prev
    Next
    INDEX
    Explanations

    Bacterial colonisation or comparison

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

    texts that contain formal or technical content, particularly documents with specialized formatting or numerical data.

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered 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
    Negative Logits
    nymi
    -1.04
    σκ
    -0.93
    Արտ
    -0.92
    pping
    -0.91
     литератур
    -0.91
    łka
    -0.90
     rask
    -0.90
     praktis
    -0.86
     passée
    -0.84
     luka
    -0.84
    POSITIVE LOGITS
    ․
    0.98
     resulted
    0.83
     Armenian
    0.81
     mentioned
    0.77
    illotine
    0.76
     cox
    0.75
     Armen
    0.75
     Yerevan
    0.75
    onyms
    0.75
     determinado
    0.75
    Activations Density 0.009%

    No Known Activations