© 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. 107245
    Prev
    Next
    INDEX
    Explanations

    grammatical markers

    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
    ная
    0.55
     законом
    0.54
     మాత్రం
    0.53
    ᱫ
    0.52
    चार
    0.50
    ская
    0.50
    vação
    0.49
     Starring
    0.49
    рую
    0.49
     제작
    0.49
    POSITIVE LOGITS
    iot
    0.62
    渤
    0.59
    ن
    0.58
     dott
    0.58
     jest
    0.57
     alcuni
    0.57
    وفي
    0.57
    可能是
    0.57
    ري
    0.56
     kosm
    0.56
    Activations Density 0.000%

    No Known Activations