© 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-16K
    7. 10639
    Prev
    Next
    INDEX
    Explanations

    warm and harmful contexts

    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
    Negative Logits
    pä
    2.09
    ა
    1.91
    kennt
    1.84
    ered
    1.79
     fern
    1.78
    pte
    1.77
     construed
    1.77
    cribed
    1.75
    pul
    1.73
     humili
    1.73
    POSITIVE LOGITS
    으로써
    2.42
    ሳሪያ
    2.33
    ल
    2.20
    ০০
    2.14
    फारिश
    2.09
    지막
    2.02
    대상
    2.02
    م
    2.00
    owane
    1.98
    otip
    1.98
    Activations Density 0.282%

    No Known Activations