© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 41348
    Prev
    Next
    INDEX
    Explanations

    Christ or Christianity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    s
    2.50
    ية
    1.94
    ים
    1.84
    ‌ی
    1.81
    𝘀
    1.80
    ς
    1.80
    izable
    1.79
     gripe
    1.79
    서
    1.72
    ется
    1.70
    POSITIVE LOGITS
    zelfde
    2.09
    ﻣ
    2.05
    ம்
    1.98
    ли
    1.90
    を確認
    1.79
    같
    1.79
    を設定
    1.78
     μεγάλη
    1.77
    ご確認
    1.77
     leggi
    1.75
    Activations Density 0.000%

    No Known Activations