© 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. 6090
    Prev
    Next
    INDEX
    Explanations

    standard definitions

    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
    -
    0.79
    ानीय
    0.70
     بأ
    0.68
     legit
    0.67
    zit
    0.65
    ándo
    0.64
    ingo
    0.64
    ressing
    0.64
     touching
    0.63
     Verd
    0.63
    POSITIVE LOGITS
    我会
    1.03
    韩
    1.00
    我已经
    0.96
    Hydrochloride
    0.95
    地铁
    0.91
    Pune
    0.89
    专辑
    0.87
    adı
    0.86
     Şubat
    0.84
    申报
    0.84
    Activations Density 0.001%

    No Known Activations