© 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. 27412
    Prev
    Next
    INDEX
    Explanations

    especially on or before

    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
    amento
    0.41
    기고
    0.41
    ική
    0.40
     இறைவன்
    0.40
     функций
    0.40
    咊
    0.40
    ๆ
    0.39
    鋼
    0.39
    variance
    0.39
     и
    0.39
    POSITIVE LOGITS
     switched
    0.44
     startling
    0.42
     beforehand
    0.40
     BEFORE
    0.39
     el
    0.38
     zuvor
    0.38
     genders
    0.38
     soorten
    0.38
     Peng
    0.38
     Katar
    0.38
    Activations Density 0.018%

    No Known Activations