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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 2304
    Prev
    Next
    INDEX
    Explanations

    past and future

    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
     불구하고
    1.76
    і
    1.70
     няко
    1.62
    an
    1.56
    н
    1.56
    ри
    1.53
    鸯
    1.53
    ια
    1.49
    доров
    1.49
    е
    1.49
    POSITIVE LOGITS
     daí
    2.14
    تك
    1.89
    رت
    1.87
    erweise
    1.79
    のマ
    1.77
    おお
    1.77
    おそらく
    1.76
    kende
    1.73
    นอก
    1.73
    ژگی
    1.73
    Activations Density 0.009%

    No Known Activations