© 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. 24-GEMMASCOPE-2-RES-262K
    7. 12733
    Prev
    Next
    INDEX
    Explanations

    as a or as being

    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_24_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    きます
    0.68
    ت
    0.62
     considerados
    0.61
    GLE
    0.60
     naszym
    0.60
     стекло
    0.60
    tart
    0.60
    া
    0.60
    DefaultFor
    0.59
     ভিত্তি
    0.58
    POSITIVE LOGITS
     Having
    0.80
     Being
    0.79
     Anthropology
    0.75
     چیزی
    0.74
     Proficiency
    0.73
     Lots
    0.72
     suffisamment
    0.72
     Planning
    0.71
     Certification
    0.71
     aad
    0.70
    Activations Density 0.001%

    No Known Activations