© 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. 40844
    Prev
    Next
    INDEX
    Explanations

    predicting "excellent" after punctuation

    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
    âmara
    0.42
    শিয়া
    0.40
     promozione
    0.38
    ब्रा
    0.38
    Mfg
    0.37
     Ordinary
    0.37
    iries
    0.37
    lela
    0.37
    ibl
    0.36
    ﭜ
    0.36
    POSITIVE LOGITS
     wow
    0.47
     Бе
    0.40
    真是
    0.39
     WOW
    0.37
    素晴らしい
    0.37
    ដ៏
    0.37
     верно
    0.36
     truly
    0.36
     भाषण
    0.36
    明白了
    0.36
    Activations Density 0.039%

    No Known Activations