© 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. 183300
    Prev
    Next
    INDEX
    Explanations

    a purpose or rationale

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

    numbers and calculations

    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
     peritoneum
    0.46
     세포
    0.46
     sahi
    0.45
     Sis
    0.45
     DNA
    0.44
     sis
    0.43
    ách
    0.43
     Inspect
    0.43
     杯
    0.43
     Fabrics
    0.43
    POSITIVE LOGITS
    methylsulfanyl
    0.46
    munic
    0.46
    مس
    0.45
    ﻲ
    0.45
    borough
    0.44
     झाल्यावर
    0.44
    詰
    0.44
    ন্তী
    0.43
    জিত
    0.43
    其他
    0.43
    Activations Density 0.001%

    No Known Activations