© 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. 72734
    Prev
    Next
    INDEX
    Explanations

    items returned, citizens, improve the website

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

    preventing from happening

    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
    text
    0.47
    两年
    0.45
    exist
    0.43
     urč
    0.43
    index
    0.42
     overstated
    0.41
    মুখি
    0.39
    underscore
    0.39
     返
    0.38
    齁
    0.38
    POSITIVE LOGITS
     đỡ
    0.45
     بونس
    0.45
     accueillir
    0.44
    ീല
    0.44
     Commiss
    0.43
     Ola
    0.43
    လဲ
    0.43
     signup
    0.42
     ڈپاز
    0.42
     Wettbewer
    0.41
    Activations Density 0.005%

    No Known Activations