© 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. 180163
    Prev
    Next
    INDEX
    Explanations

    words after "to"

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

    resell, acquire, shell

    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
     website
    0.48
     Compiler
    0.47
     e
    0.46
     wherein
    0.46
    wherein
    0.46
     Diocese
    0.46
     Studies
    0.45
     Library
    0.45
     Website
    0.45
     agus
    0.45
    POSITIVE LOGITS
     ಖರೀದ
    0.53
    調節
    0.49
     своїх
    0.49
     vyroben
    0.47
     آتا
    0.47
    寶寶
    0.47
    雛
    0.46
     अंडे
    0.46
     اسلح
    0.46
     কেনার
    0.45
    Activations Density 0.001%

    No Known Activations