© 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. 221134
    Prev
    Next
    INDEX
    Explanations

    Marijuana, lifts, lobby, brethren

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

    "you are" or "scientists are"

    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
    芷
    0.50
    "/
    0.47
    𝑪
    0.43
    /"
    0.43
    "",
    0.42
    玲
    0.42
     Greece
    0.41
    ופ
    0.41
    মধ্যে
    0.41
     SOR
    0.41
    POSITIVE LOGITS
     petroleum
    0.58
     पेट्रोलियम
    0.49
     humorous
    0.46
     chuck
    0.44
    ܠܐ
    0.42
     chuckled
    0.42
     Petroleum
    0.42
    GCC
    0.42
    Ě
    0.41
     Chuck
    0.41
    Activations Density 0.000%

    No Known Activations