© 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-16K
    7. 7630
    Prev
    Next
    INDEX
    Explanations

    Python code examples

    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_16k_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
    ل
    4.13
    で
    3.78
    야
    3.55
    ти
    3.52
    ার
    3.11
    س
    3.02
    에서
    2.98
    ov
    2.86
    arı
    2.66
    어
    2.59
    POSITIVE LOGITS
     এছাড়া
    2.19
    "{
    2.17
     وعلى
    2.03
    将
    1.96
    𝟘
    1.91
    外的
    1.88
    ""
    1.84
    "%
    1.84
    i
    1.79
    いない
    1.77
    Activations Density 0.229%

    No Known Activations