© 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. 200200
    Prev
    Next
    INDEX
    Explanations

    don't just

    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
    pector
    0.46
    igel
    0.46
    掖
    0.43
    jenkins
    0.42
    ה
    0.42
    regel
    0.41
    ijker
    0.41
    匣
    0.39
     психо
    0.39
     இரா
    0.39
    POSITIVE LOGITS
     metabol
    0.46
    linkColor
    0.44
    瑋
    0.41
     る
    0.41
    လီ
    0.41
    ੴ
    0.41
    ائیگی
    0.40
    already
    0.40
    ร็จ
    0.40
     starg
    0.39
    Activations Density 0.006%

    No Known Activations