© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 113978
    Prev
    Next
    INDEX
    Explanations

    bit.ly, goo.gl, geni.us URLs

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

    shortened URLs, particularly those using URL shortening services like "bit.ly" and "goo.gl".

    oai_token-act-pair · claude-4-5-sonnet
    Triggered by @bfgcn7frf5
    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
     by
    -1.82
     which
    -1.66
     with
    -1.63
     has
    -1.59
     and
    -1.54
     because
    -1.51
     for
    -1.49
    。。。。
    -1.48
     навіть
    -1.46
     sexto
    -1.46
    POSITIVE LOGITS
    u
    1.50
     refroid
    1.45
     mediocre
    1.45
     ระ
    1.42
    还是很
    1.41
    imo
    1.41
     této
    1.39
     améliorer
    1.38
     intellig
    1.38
    p
    1.38
    Activations Density 0.031%

    No Known Activations