© 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. 235677
    Prev
    Next
    INDEX
    Explanations

    legal judgments and filings

    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
    -
    0.48
    es
    0.46
    लीम
    0.46
    лся
    0.46
    ланд
    0.45
    ék
    0.44
     от
    0.44
    ියා
    0.44
    ispiele
    0.43
    atique
    0.43
    POSITIVE LOGITS
    塗
    0.49
     দুনি
    0.46
     Букмекер
    0.44
     repug
    0.44
     rambling
    0.44
     disagreeable
    0.43
     Tujuan
    0.43
     misguided
    0.43
     tujuan
    0.42
     हिंसा
    0.42
    Activations Density 0.001%

    No Known Activations