© 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. 211848
    Prev
    Next
    INDEX
    Explanations

    resources, spyware, addition, and collided

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

    network communication or transportation

    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
     enthalpies
    0.50
     choppy
    0.48
    也要
    0.47
     edged
    0.47
    σό
    0.47
    だけ
    0.46
    DEG
    0.46
    ら
    0.45
     চাহিল
    0.45
     enthalpy
    0.45
    POSITIVE LOGITS
    ."[
    0.53
    ..."
    0.52
     tuv
    0.50
     Transportation
    0.48
    ()"
    0.48
     المع
    0.48
     Erit
    0.48
     Trans
    0.47
     satisfacer
    0.47
    .."
    0.47
    Activations Density 0.000%

    No Known Activations