© 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-262K
    7. 170427
    Prev
    Next
    INDEX
    Explanations

    date, reversed, tricky, indicates

    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
     aka
    0.44
    \
    0.44
     accessor
    0.41
     squad
    0.41
     murky
    0.41
    ings
    0.40
     accessories
    0.40
     #
    0.39
     rhe
    0.39
    ナ
    0.39
    POSITIVE LOGITS
    지와
    0.54
    উদাহরণ
    0.52
     있고
    0.47
     bijvoorbeeld
    0.47
    욌
    0.47
    었고
    0.46
    那时
    0.46
     décadas
    0.46
     doenças
    0.46
     errichtet
    0.45
    Activations Density 0.009%

    No Known Activations