© 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. 11280
    Prev
    Next
    INDEX
    Explanations

    authentication contexts

    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
     or
    -1.41
     if
    -1.30
     time
    -1.12
     so
    -1.09
     because
    -1.08
     after
    -1.06
     или
    -1.04
     then
    -1.03
     still
    -1.02
     just
    -1.00
    POSITIVE LOGITS
     två
    1.14
    respectively
    1.09
     двох
    1.07
    tratamiento
    1.06
    zwei
    1.06
    deux
    1.06
     beiden
    1.06
    buenos
    1.05
     ciment
    1.02
    tableWidget
    1.02
    Activations Density 0.018%

    No Known Activations