© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 152991
    Prev
    Next
    INDEX
    Explanations

    financial and medical terms

    np_acts-logits-general · gemini-2.5-flash-lite

    operation on, slow, study, receptor subtype, fostered a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ный
    0.52
    三个
    0.49
    偻
    0.47
     двумя
    0.47
    three
    0.47
    тори
    0.46
     اثنين
    0.46
    两个
    0.45
    兩個
    0.45
     I
    0.45
    POSITIVE LOGITS
     vállalat
    0.48
     PFAS
    0.43
     amph
    0.42
    ণ্ডল
    0.42
     támogat
    0.42
     salaire
    0.41
     él
    0.40
     wyja
    0.40
     macroph
    0.40
     drugg
    0.40
    Activations Density 0.001%

    No Known Activations