© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 387
    Prev
    Next
    INDEX
    Explanations

    the followed by a word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     />
    0.23
    および
    0.23
     \
    0.22
    nThe
    0.21
    ()
    0.21
     _
    0.21
     The
    0.21
     >
    0.20
    sofar
    0.20
     ﺍ
    0.20
    POSITIVE LOGITS
     slightest
    0.24
     smartest
    0.24
     funniest
    0.23
     wildest
    0.23
     mêmes
    0.23
     tini
    0.23
     proverbial
    0.23
     onus
    0.22
     loudest
    0.22
    га
    0.21
    Activations Density 3.006%

    No Known Activations