© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128685
    Prev
    Next
    INDEX
    Explanations

    numbers and order

    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
    Not in Any Lists

    No Comments

    Negative Logits
    titre
    -0.73
    transactions
    -0.72
    ятся
    -0.72
     performances
    -0.72
     Priya
    -0.70
    treat
    -0.69
    🛎
    -0.69
    AccountName
    -0.68
    innis
    -0.68
    laptop
    -0.68
    POSITIVE LOGITS
     obligado
    0.80
     arasında
    0.79
     different
    0.78
     가장
    0.76
     másik
    0.75
    異なる
    0.73
    で一番
    0.73
    蒺
    0.72
    错了
    0.72
     aveva
    0.71
    Activations Density 0.179%

    No Known Activations