© 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. 15558
    Prev
    Next
    INDEX
    Explanations

    why did jokes

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

    why don't skeletons/scientists

    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
    Однако
    0.44
    スク
    0.44
    profitLoss
    0.43
    정이
    0.43
    Лу
    0.43
    ヌ
    0.42
    吕
    0.42
    да
    0.42
    기를
    0.42
    景
    0.41
    POSITIVE LOGITS
     tieto
    0.51
     autour
    0.49
     aantal
    0.48
     partito
    0.48
     antal
    0.48
     mehr
    0.48
     jauh
    0.47
     mostrado
    0.47
     sung
    0.47
    unidad
    0.46
    Activations Density 0.001%

    No Known Activations