© 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. 84503
    Prev
    Next
    INDEX
    Explanations

    cities, departments, and institutions

    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
     of
    -1.30
     now
    -1.25
     that
    -1.19
     often
    -1.12
     necessary
    -1.12
     only
    -1.10
    :
    -1.09
     było
    -1.06
     the
    -1.05
     so
    -1.05
    POSITIVE LOGITS
     vinaigre
    1.23
     portefeuille
    1.23
     gelatina
    1.17
     réservoir
    1.16
     trésor
    1.16
     vœ
    1.15
     revêtement
    1.13
     fidèle
    1.13
    âne
    1.13
    komme
    1.11
    Activations Density 0.010%

    No Known Activations