© 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. 2706
    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
    {
    0.64
    що
    0.61
    Paper
    0.58
    *[
    0.56
    channel
    0.56
    Channel
    0.56
    anchor
    0.55
    [*
    0.55
    事务
    0.54
    RDD
    0.54
    POSITIVE LOGITS
     Plumbing
    0.58
     Nails
    0.58
     Bathroom
    0.56
     Saltar
    0.53
     bebé
    0.52
     boobs
    0.50
     Colored
    0.50
     বস
    0.50
     Zahl
    0.50
     Toilet
    0.50
    Activations Density 0.013%

    No Known Activations