© 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. 11773
    Prev
    Next
    INDEX
    Explanations

    Initializes, commences

    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
    leri
    0.89
     gevol
    0.88
    gio
    0.86
    文档
    0.84
     laki
    0.84
    存于互联网档案馆
    0.83
    odont
    0.80
    疗
    0.80
     podob
    0.79
    ron
    0.79
    POSITIVE LOGITS
    ر
    0.83
     commences
    0.74
     многих
    0.74
     الماضي
    0.74
     изменений
    0.73
     niemals
    0.73
     وام
    0.71
     ensues
    0.71
    ี
    0.71
     Initializes
    0.70
    Activations Density 0.000%

    No Known Activations