© 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. 32739
    Prev
    Next
    INDEX
    Explanations

    abbreviations and code snippets

    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
     képes
    -1.05
    ningarna
    -0.84
     emlé
    -0.82
     kerül
    -0.82
     vzdu
    -0.81
     who
    -0.81
     változ
    -0.81
     törvény
    -0.81
     аппетита
    -0.78
     Startseite
    -0.77
    POSITIVE LOGITS
     Seoul
    0.91
     BaseActivity
    0.90
     הוא
    0.90
     ње
    0.90
     dla
    0.89
    谧
    0.86
     ド
    0.86
    ख़
    0.85
    goth
    0.85
    atisme
    0.84
    Activations Density 0.027%

    No Known Activations