© 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. 192614
    Prev
    Next
    INDEX
    Explanations

    local population, November 5, Thanks so much, medical emergency

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

    without sacrificing quality

    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
     crée
    0.54
     takım
    0.53
    墂
    0.53
     trabalha
    0.52
     flotte
    0.52
     produz
    0.51
     wypeł
    0.51
     réduire
    0.51
     trabaja
    0.51
     içeri
    0.51
    POSITIVE LOGITS
    Mbps
    0.42
     there
    0.42
    There
    0.42
     architects
    0.42
    Го
    0.42
    𝐽
    0.42
    Че
    0.41
    Υ
    0.41
    Еще
    0.41
    attacks
    0.40
    Activations Density 0.001%

    No Known Activations