© 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. 103652
    Prev
    Next
    INDEX
    Explanations

    profit, name, flux, email, controls, page, $, fringe

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

    numbers and phrases

    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
    θν
    0.54
    𒀝
    0.51
    ース
    0.50
    StudentID
    0.50
    relativistic
    0.50
    Callories
    0.49
    MoodAnalyser
    0.47
    ন্যাশনাল
    0.47
    rufen
    0.47
    ٰی
    0.47
    POSITIVE LOGITS
     IN
    0.46
    ين
    0.43
    -
    0.43
     лиш
    0.43
     :
    0.43
     как
    0.43
     acompanhar
    0.43
     prev
    0.42
     са
    0.42
    て
    0.42
    Activations Density 0.001%

    No Known Activations