© 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-65K
    7. 30
    Prev
    Next
    INDEX
    Explanations

    storage size (GBs)

    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_65k_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
    ྰ
    0.54
     አካ
    0.50
     ቦ
    0.49
    জীবনে
    0.47
     জীবনে
    0.47
    .'/
    0.46
     dañ
    0.46
     reunification
    0.46
    מ
    0.46
     ዳ
    0.45
    POSITIVE LOGITS
     Schluss
    0.48
    至
    0.46
    啐
    0.46
     Benchmark
    0.43
     benchmark
    0.43
    etext
    0.41
    ร้อม
    0.41
    вах
    0.41
    可能性
    0.40
    症状
    0.40
    Activations Density 0.010%

    No Known Activations