© 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. 213446
    Prev
    Next
    INDEX
    Explanations

    created in

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

    container {

    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
     truncation
    0.51
     particles
    0.46
     車
    0.46
     homotopy
    0.46
     crossover
    0.46
    ESE
    0.45
     mutant
    0.44
     particle
    0.44
     py
    0.44
     problem
    0.43
    POSITIVE LOGITS
    স
    0.55
    babel
    0.53
    𝚙
    0.52
    anud
    0.51
    पों
    0.50
    每一
    0.50
    ພວກເຮົາ
    0.49
     पुस्तकें
    0.48
    (&(*
    0.48
    ພວກເຮ
    0.48
    Activations Density 0.002%

    No Known Activations