© 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. 10-GEMMASCOPE-RES-131K
    7. 114189
    Prev
    Next
    INDEX
    Explanations

    numbered sequences and chemical names

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

    sequences of numeric digits, especially when they appear in code or data formats.

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Ciebie
    -1.57
    孃
    -1.48
    olução
    -1.47
    部分を
    -1.46
    OCOLATE
    -1.45
     vuitton
    -1.40
    tahui
    -1.39
    字节
    -1.38
    zości
    -1.38
    $).
    -1.36
    POSITIVE LOGITS
     to
    1.92
    不同的
    1.66
    truly
    1.57
     portrayed
    1.53
    不同
    1.46
    Gön
    1.45
    各种
    1.45
    ὸν
    1.43
     understands
    1.38
     sfondo
    1.38
    Activations Density 0.038%

    No Known Activations