© 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. 22-GEMMASCOPE-RES-131K
    7. 32764
    Prev
    Next
    INDEX
    Explanations

    code and markup languages

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ométrique
    -1.10
    atória
    -1.08
    鸰
    -1.03
    ザイン
    -0.99
     Subject
    -0.94
     December
    -0.91
    FileSize
    -0.91
     NF
    -0.90
     McC
    -0.89
    扎
    -0.89
    POSITIVE LOGITS
    热闹
    0.99
     namelijk
    0.97
     scaly
    0.96
     anyhow
    0.94
     confirmación
    0.93
    这位
    0.89
    приклад
    0.89
    panes
    0.89
     DKI
    0.88
     "'";
    0.88
    Activations Density 0.092%

    No Known Activations