© 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. 45530
    Prev
    Next
    INDEX
    Explanations

    before or prior events

    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
     Greedy
    0.45
     greed
    0.43
     Erik
    0.42
     Fun
    0.39
     fun
    0.39
     Fa
    0.39
     Faith
    0.39
    顺
    0.38
    عه
    0.38
    遗传
    0.38
    POSITIVE LOGITS
     lawyer
    0.48
     antes
    0.47
     bevor
    0.46
     sebelum
    0.45
    嶄
    0.44
    before
    0.44
     rises
    0.44
     prior
    0.44
    Before
    0.43
    prior
    0.43
    Activations Density 0.050%

    No Known Activations