© 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. 15882
    Prev
    Next
    INDEX
    Explanations

    programming keywords or identifiers

    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
     even
    -0.92
    érc
    -0.90
     demonstrated
    -0.90
     JMenuItem
    -0.89
     those
    -0.89
    Личная
    -0.87
    rangian
    -0.86
     similarly
    -0.86
     aggiunge
    -0.85
     crisi
    -0.84
    POSITIVE LOGITS
     genoux
    1.26
     symptômes
    1.20
     congrès
    1.17
     flesta
    1.08
     intitulé
    1.03
     vélos
    1.02
     jugadores
    1.02
     overall
    1.01
    Földrajz
    1.01
    cosx
    1.00
    Activations Density 0.088%

    No Known Activations