© 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. 9787
    Prev
    Next
    INDEX
    Explanations

    alphanumeric characters and symbols

    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
    merken
    -1.02
     ROOMS
    -1.00
    erunner
    -0.98
     soucis
    -0.98
    kijk
    -0.98
    invokeLater
    -0.98
     doigt
    -0.96
     SCHOOLS
    -0.96
     ROMAN
    -0.96
     exercícios
    -0.96
    POSITIVE LOGITS
     occasionally
    1.29
     algunas
    1.10
     various
    1.05
     occasional
    1.04
     permitted
    1.02
     sometimes
    1.01
     widely
    0.99
     reasonable
    0.99
     các
    0.98
     some
    0.98
    Activations Density 0.021%

    No Known Activations