© 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. 114169
    Prev
    Next
    INDEX
    Explanations

    mixed types of things

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    <em>
    -1.52
    ↵↵
    -1.48
     to
    -1.45
       
    -1.38
     FOR
    -1.36
    🌼
    -1.35
     would
    -1.28
    <strong>
    -1.28
     that
    -1.23
    <b>
    -1.23
    POSITIVE LOGITS
    mixed
    1.84
     mixed
    1.78
     Mixed
    1.73
    Mixed
    1.66
    uttgart
    1.61
     mix
    1.55
     mélanger
    1.52
    混合
    1.52
    endalikan
    1.51
     envelo
    1.48
    Activations Density 0.053%

    No Known Activations