© 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. 31-GEMMASCOPE-2-RES-262K
    7. 21808
    Prev
    Next
    INDEX
    Explanations

    listing features and terms

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     insulina
    0.52
     xương
    0.48
    يط
    0.48
     économiques
    0.46
     calorías
    0.46
     líneas
    0.45
    тата
    0.45
     ở
    0.44
     behöver
    0.44
    一个小
    0.44
    POSITIVE LOGITS
     Tengo
    0.40
    。
    0.40
    प्पो
    0.39
    རྒྱ
    0.39
    <tr>
    0.38
    פע
    0.38
    ജ്
    0.38
    лү
    0.38
    OC
    0.37
    MIB
    0.37
    Activations Density 0.003%

    No Known Activations