Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 2356
    Prev
    Next
    INDEX
    Explanations

    abstracts and section introductions

    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_31_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
     bạn
    0.50
     quieres
    0.46
     شما
    0.45
     Bạn
    0.45
     giphy
    0.45
     あなた
    0.43
     ivvu
    0.43
    傥
    0.42
     você
    0.42
     yummy
    0.41
    POSITIVE LOGITS
     $\
    0.45
     IEEE
    0.43
    IEEE
    0.43
     Keywords
    0.41
    Keywords
    0.40
     Manuscript
    0.40
     Accepted
    0.39
    $\
    0.38
    {\
    0.38
    Abstract
    0.38
    Activations Density 0.022%

    No Known Activations