© 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. 12-GEMMASCOPE-2-RES-262K
    7. 34520
    Prev
    Next
    INDEX
    Explanations

    unknown

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    te
    1.90
    y
    1.72
     aggrieved
    1.70
     caesar
    1.61
    י
    1.51
    ം
    1.51
     starving
    1.48
    ি
    1.45
    ು
    1.45
     dragging
    1.45
    POSITIVE LOGITS
    Е
    1.91
    ज
    1.63
    I
    1.62
    כ
    1.57
    ير
    1.56
    त
    1.54
     расти
    1.49
    𝐃
    1.49
    ت
    1.47
     vitesses
    1.46
    Activations Density 0.003%

    No Known Activations