© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 35746
    Prev
    Next
    INDEX
    Explanations

    programming keywords and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ة
    0.77
    д
    0.74
    дные
    0.59
    ш
    0.57
    ala
    0.55
    it
    0.55
    ט
    0.55
    يت
    0.54
    т
    0.53
     ट्रॉपिकल
    0.52
    POSITIVE LOGITS
     filesize
    0.55
     film
    0.55
    film
    0.52
     begins
    0.52
     grabs
    0.50
     sensations
    0.49
     convictions
    0.47
    PC
    0.46
    ri
    0.46
     editions
    0.46
    Activations Density 0.000%

    No Known Activations