© 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. 11391
    Prev
    Next
    INDEX
    Explanations

    you're contractions

    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
     membahas
    0.43
    سيط
    0.42
    מס
    0.40
    으
    0.40
     stets
    0.40
     từng
    0.39
    르
    0.39
    生日
    0.38
     tartış
    0.38
    वड
    0.37
    POSITIVE LOGITS
     probably
    0.49
     correctly
    0.45
    probably
    0.43
     melakukannya
    0.42
    きっと
    0.41
     නොව
    0.41
     probablement
    0.40
     unwittingly
    0.40
     hacerlo
    0.40
     جاسک
    0.40
    Activations Density 0.171%

    No Known Activations