© 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. 15430
    Prev
    Next
    INDEX
    Explanations

    daily puzzles and word games

    np_acts-logits-general · gemini-2.5-flash-lite

    start with "en", "core keyword", "atom netbooks"

    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
    ēi
    0.54
    циа
    0.53
    czaj
    0.53
    χ
    0.52
    ή
    0.51
    ηση
    0.51
    گذ
    0.50
    м
    0.50
    ну
    0.50
     estágio
    0.50
    POSITIVE LOGITS
     Called
    0.46
     inbox
    0.45
     keen
    0.44
     spoon
    0.43
     Catch
    0.41
     bowling
    0.41
     called
    0.41
     WALK
    0.41
     WALKER
    0.40
     Logger
    0.40
    Activations Density 0.002%

    No Known Activations