© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 157
    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
    Negative Logits
    0.58
     optimizations
    0.48
     parameterized
    0.48
     concatenated
    0.47
     ~/.
    0.46
     GPUs
    0.46
     concatenate
    0.46
     à
    0.46
     GPU
    0.45
     と
    0.45
    POSITIVE LOGITS
     personali
    0.59
    듦
    0.58
     fortitude
    0.55
    <unused2123>
    0.54
     personnelle
    0.52
    judgment
    0.51
     upheaval
    0.51
     треба
    0.50
    financ
    0.50
     contentment
    0.49
    Activations Density 1.252%

    No Known Activations