© 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-262K
    7. 24596
    Prev
    Next
    INDEX
    Explanations

    flight returns, microaggressions, sales, phenomena

    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_262k_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
    ׄ
    0.41
    ूल
    0.39
    ্রিয়া
    0.39
     tenure
    0.38
    ティーク
    0.37
     lease
    0.37
     видов
    0.37
    ዐ
    0.36
     coarse
    0.36
    Resizable
    0.36
    POSITIVE LOGITS
    用来
    0.43
    我们要
    0.43
     believers
    0.41
    憉
    0.40
    currentTime
    0.39
     Used
    0.38
     used
    0.38
    erais
    0.38
    诱
    0.38
    用于
    0.38
    Activations Density 0.000%

    No Known Activations