© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 4021
    Prev
    Next
    INDEX
    Explanations

    definite article phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     the
    0.26
     using
    0.25
    ↵
    0.25
    the
    0.25
    Using
    0.24
     another
    0.24
     some
    0.23
     a
    0.23
     The
    0.22
    using
    0.22
    POSITIVE LOGITS
     onus
    0.32
    ophylline
    0.31
    mselves
    0.28
     slightest
    0.28
     meisten
    0.28
     physicality
    0.27
     entirety
    0.27
     impetus
    0.27
     aforementioned
    0.27
     interplay
    0.27
    Activations Density 0.827%

    No Known Activations