© 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. 98778
    Prev
    Next
    INDEX
    Explanations

    Artificial intelligence and neural networks

    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
    \
    -2.80
     lament
    -2.33
     mystère
    -2.27
    メイド
    -2.19
    sandalia
    -2.17
     pembun
    -2.16
    私は
    -2.14
     mangled
    -2.11
    无敌
    -2.09
     bunch
    -2.08
    POSITIVE LOGITS
    他也
    3.02
    </h4>
    2.98
     That
    2.86
    ”,
    2.81
    𓄹
    2.78
    “
    2.70
    g
    2.67
    ”:
    2.66
    ?”
    2.61
    酲
    2.56
    Activations Density 0.004%

    No Known Activations