© 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. 140020
    Prev
    Next
    INDEX
    Explanations

    link about, onion recipes

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

    jQuery Core Concepts

    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
     and
    0.44
    mj
    0.41
     aquatic
    0.41
     recipients
    0.40
     concussion
    0.39
     inmates
    0.39
     backcountry
    0.38
    -
    0.38
    ins
    0.38
     gaming
    0.38
    POSITIVE LOGITS
     მთავ
    0.48
    鐟
    0.48
     setToDefault
    0.46
     핵심
    0.46
     началь
    0.45
     💞
    0.44
    ដើ
    0.44
    🩷
    0.43
     superClass
    0.42
     Omphalodes
    0.42
    Activations Density 0.001%

    No Known Activations