© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 7142
    Prev
    Next
    INDEX
    Explanations

    agricultural, Python, challenges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    了
    0.99
     د
    0.99
    و
    0.95
     Unknown
    0.95
     Supplies
    0.92
     SP
    0.92
     Sol
    0.91
     موجود
    0.91
     Victor
    0.91
     $[
    0.90
    POSITIVE LOGITS
     steadily
    1.11
    destination
    1.05
    sourceforge
    0.99
    cons
    0.99
    against
    0.98
    inte
    0.96
    coding
    0.96
     warmly
    0.96
     seamlessly
    0.95
     quickly
    0.95
    Activations Density 0.001%

    No Known Activations