© 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. 15595
    Prev
    Next
    INDEX
    Explanations

    special tokens and prefixes

    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
    ni
    3.27
    تي
    2.95
    d
    2.89
    র
    2.80
    p
    2.73
    m
    2.72
    li
    2.69
    liği
    2.64
    g
    2.59
    ز
    2.58
    POSITIVE LOGITS
    에게
    2.05
    pt
    2.02
    が高
    2.00
    ▾
    1.95
    தான்
    1.94
    다
    1.92
    ły
    1.91
    ze
    1.90
    が多く
    1.87
    ş
    1.87
    Activations Density 0.233%

    No Known Activations