© 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. 10-GEMMASCOPE-RES-131K
    7. 84597
    Prev
    Next
    INDEX
    Explanations

    linking descriptive qualities

    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
    Not in Any Lists

    No Comments

    Negative Logits
     verranno
    -1.77
    ܇
    -1.74
     тільки
    -1.70
     PRODUCTO
    -1.67
     sarebbero
    -1.65
    gorro
    -1.64
    Общие
    -1.59
     العديد
    -1.56
     passaram
    -1.56
     ludzie
    -1.55
    POSITIVE LOGITS
     or
    1.94
     cueva
    1.77
     casos
    1.67
    źć
    1.53
     aldea
    1.52
     amount
    1.50
     neue
    1.50
     about
    1.49
     '
    1.49
     how
    1.48
    Activations Density 0.065%

    No Known Activations