© 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. 83908
    Prev
    Next
    INDEX
    Explanations

    mixed signal, mode, or use

    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
    {
    -1.92
    tividade
    -1.53
    herstellung
    -1.38
    嫱
    -1.38
    龶
    -1.35
    niosek
    -1.30
    に応
    -1.29
    '";
    -1.27
     Instead
    -1.27
    getNome
    -1.26
    POSITIVE LOGITS
    HasIndex
    1.59
    膈
    1.56
    中略
    1.55
    翃
    1.48
     erhi
    1.48
     grava
    1.46
    咈
    1.45
    混合
    1.45
    ⢦
    1.43
     forsake
    1.42
    Activations Density 0.035%

    No Known Activations