© 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. 3173
    Prev
    Next
    INDEX
    Explanations

    defer cleanup actions

    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
    ટ
    0.97
    特色
    0.95
     оформления
    0.89
    ون
    0.88
    ای
    0.88
    霑
    0.87
    Circ
    0.84
    ページ
    0.84
     حروف
    0.83
    B
    0.83
    POSITIVE LOGITS
    ended
    0.91
     ਹ
    0.87
    是一種
    0.87
     WndProc
    0.82
     Поэтому
    0.81
     Dub
    0.78
    ANAL
    0.78
     eus
    0.78
     Ya
    0.77
     inim
    0.77
    Activations Density 0.002%

    No Known Activations