© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 2772
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_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
     prioritization
    0.61
     priorit
    0.58
     broom
    0.57
     prioritizing
    0.54
    दर्शिता
    0.53
    箴
    0.53
     hilft
    0.52
    擇
    0.52
     ஏற்படுத்த
    0.50
     brind
    0.50
    POSITIVE LOGITS
     التعامل
    1.58
     interacting
    1.41
    ใช้งาน
    1.36
    操作
    1.34
     accessing
    1.27
    扱う
    1.25
     manipulating
    1.23
     usage
    1.20
     mengakses
    1.19
     dealings
    1.18
    Activations Density 1.520%

    No Known Activations