© 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. 246981
    Prev
    Next
    INDEX
    Explanations

    packing and shipping goods

    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
    isant
    0.55
     অনুযায়ী
    0.46
    ،
    0.43
    Sanchez
    0.42
    egaard
    0.41
     nonchal
    0.41
    istisch
    0.41
     justices
    0.41
    ezza
    0.41
     Justices
    0.40
    POSITIVE LOGITS
     userData
    0.53
    구
    0.51
    Источник
    0.49
    Референ
    0.49
     Як
    0.48
     grupos
    0.47
    ियोग
    0.45
    িল্ল
    0.45
    CodeDom
    0.45
    Обра
    0.45
    Activations Density 0.001%

    No Known Activations