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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 9692
    Prev
    Next
    INDEX
    Explanations

    Julie Maxton or Premature

    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
     that
    -1.09
     information
    -1.00
     an
    -0.99
    ƌ
    -0.95
     text
    -0.93
    文書
    -0.93
     quickly
    -0.92
     briefly
    -0.92
     телефон
    -0.91
     Mädchen
    -0.90
    POSITIVE LOGITS
     querían
    1.16
     empezaron
    1.16
     tomaron
    1.14
    InputTagHelper
    1.05
     comenzaron
    1.05
     pusieron
    1.04
     dejaron
    1.02
    Largeur
    1.01
     quedaron
    1.00
     sév
    0.99
    Activations Density 0.002%

    No Known Activations