© 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. 15106
    Prev
    Next
    INDEX
    Explanations

    //

    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
    ০
    1.87
    ت
    1.65
    >',
    1.53
    𝗔
    1.52
    től
    1.50
    𝗶
    1.48
    ierten
    1.45
    𝗧
    1.45
    ১৫
    1.45
    {"
    1.41
    POSITIVE LOGITS
     upscale
    1.62
     fron
    1.40
     init
    1.38
     actu
    1.37
     dgn
    1.33
     dessous
    1.28
     vuln
    1.28
     Earn
    1.26
     turbulent
    1.25
     dorp
    1.24
    Activations Density 0.058%

    No Known Activations