© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 1235
    Prev
    Next
    INDEX
    Explanations

    enumerating items

    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_16k_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
    让你
    0.43
    urgy
    0.43
     nasıl
    0.39
    为你
    0.38
    甚至是
    0.38
    😵
    0.38
     nejen
    0.38
     እንኳን
    0.38
     মানুষকে
    0.38
     মানুষ
    0.38
    POSITIVE LOGITS
     numerous
    0.60
     ஏராளமான
    0.59
     a
    0.57
     an
    0.57
     three
    0.56
     számos
    0.55
     has
    0.54
     numerosi
    0.54
     имеет
    0.53
     numerosos
    0.52
    Activations Density 0.347%

    No Known Activations