© 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. 72224
    Prev
    Next
    INDEX
    Explanations

    significant impact or cost

    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
     for
    -2.34
     instead
    -1.80
     Instead
    -1.75
    for
    -1.73
    at
    -1.58
    чя
    -1.57
    on
    -1.55
    <i>
    -1.54
    愉快
    -1.53
     For
    -1.52
    POSITIVE LOGITS
     nhưng
    1.80
     высокая
    1.74
    うれしい
    1.72
    余談
    1.70
     และ
    1.66
    鬲
    1.62
    さっき
    1.62
     poderoso
    1.59
    僕も
    1.58
     několik
    1.56
    Activations Density 0.032%

    No Known Activations