© 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. 170548
    Prev
    Next
    INDEX
    Explanations

    Notwithstanding anything to the contrary

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

    implies or indicates meaning

    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
    (/
    0.44
    sth
    0.43
     ಅವನ
    0.43
     aquilo
    0.43
    =[
    0.42
     constitue
    0.42
     elucidate
    0.42
     corrects
    0.42
    crackers
    0.42
     concludes
    0.41
    POSITIVE LOGITS
    䀨
    0.50
    되며
    0.49
     لش
    0.44
    ลำ
    0.43
     pomoći
    0.43
    órico
    0.42
    erté
    0.42
    ตำ
    0.41
     بیت
    0.41
     рыб
    0.41
    Activations Density 0.001%

    No Known Activations