© 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. 56498
    Prev
    Next
    INDEX
    Explanations

    availability, modern grilles

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

    amazing to Watch

    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
    墜
    0.51
    歌手
    0.50
     entspricht
    0.49
    音
    0.47
    本质
    0.47
     isAuthenticated
    0.47
    朴
    0.45
    诈
    0.45
    明星
    0.43
    WORDS
    0.43
    POSITIVE LOGITS
    akan
    0.55
    רים
    0.49
     commerciaux
    0.46
     demande
    0.45
    rill
    0.44
    icar
    0.44
    utos
    0.43
    রক্ষ
    0.43
     overcrowding
    0.43
    制限
    0.43
    Activations Density 0.000%

    No Known Activations