© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 127861
    Prev
    Next
    INDEX
    Explanations

    I'm not saying X, but Y

    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
    Not in Any Lists

    No Comments

    Negative Logits
    害怕
    0.47
    ্যাল
    0.47
    胼
    0.47
    你需要
    0.43
    ्यू
    0.42
    じゃない
    0.42
    Halloween
    0.42
    صر
    0.41
    цата
    0.41
    秉
    0.41
    POSITIVE LOGITS
     результаты
    0.52
     дов
    0.50
     прожи
    0.50
     eighteen
    0.47
     இதன்
    0.47
     ஏழு
    0.47
     реки
    0.46
     וא
    0.46
     sonuç
    0.46
     खेतों
    0.46
    Activations Density 0.009%

    No Known Activations