© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 12293
    Prev
    Next
    INDEX
    Explanations

    once

    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_40_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
    时
    0.39
    ÉR
    0.39
     ત્યારે
    0.37
    Ɗ
    0.37
    时不
    0.36
    occas
    0.35
    ્યૂ
    0.35
     तब्
    0.35
    LessThan
    0.34
    綪
    0.34
    POSITIVE LOGITS
     once
    3.14
     Once
    2.86
    Once
    2.83
    once
    2.73
    一旦
    2.70
     einmal
    2.09
     एकदा
    2.03
     sekali
    1.98
     한번
    1.88
     একবার
    1.80
    Activations Density 0.237%

    No Known Activations