© 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. 31-GEMMASCOPE-2-RES-262K
    7. 9366
    Prev
    Next
    INDEX
    Explanations

    calculations and percentages

    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
    Negative Logits
     işte
    0.43
    是我们
    0.42
     ().
    0.42
     thyme
    0.42
     시작
    0.40
     muszą
    0.40
     timeliness
    0.40
     rhyme
    0.40
     الآن
    0.39
    ())+
    0.39
    POSITIVE LOGITS
    こちらも
    0.48
    national
    0.41
    ompany
    0.40
     こちら
    0.39
    こちらの
    0.38
    aign
    0.36
    branded
    0.36
    ទទួល
    0.36
    उत्तर
    0.36
     brutal
    0.36
    Activations Density 0.002%

    No Known Activations