© 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. 113987
    Prev
    Next
    INDEX
    Explanations

    test and trial run

    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
     Following
    -1.64
    \
    -1.53
    føring
    -1.50
     måned
    -1.49
     For
    -1.47
     nowa
    -1.46
    før
    -1.42
     xxiii
    -1.42
    nummer
    -1.41
    fondos
    -1.41
    POSITIVE LOGITS
     ausreich
    2.17
     使っ
    1.95
     también
    1.79
    also
    1.71
    べく
    1.64
    筈
    1.59
     également
    1.58
     красивые
    1.55
     your
    1.52
    man
    1.52
    Activations Density 0.012%

    No Known Activations