© 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. 380
    Prev
    Next
    INDEX
    Explanations

    my purpose or programming

    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_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
    。
    0.30
    Cell
    0.28
    Skin
    0.27
     Cell
    0.27
    Id
    0.27
    喜欢的
    0.26
     {
    0.26
    และ
    0.26
    Its
    0.26
    {
    0.25
    POSITIVE LOGITS
     ability
    0.36
     emphasis
    0.36
     usefulness
    0.36
     inability
    0.35
     effectiveness
    0.35
     scalability
    0.35
     efforts
    0.34
     reliance
    0.34
     adaptability
    0.34
     profitability
    0.33
    Activations Density 0.595%

    No Known Activations