© 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. 207886
    Prev
    Next
    INDEX
    Explanations

    download extent stock

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

    optimization and scientific computing

    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
    ｸ
    0.50
     ク
    0.48
     renseignements
    0.46
    alls
    0.46
     야
    0.46
     utilisent
    0.45
     ま
    0.45
    ENERGY
    0.45
    それぞれ
    0.45
    エネルギー
    0.45
    POSITIVE LOGITS
    ية
    0.49
    ipzig
    0.48
     Meinung
    0.47
     Thess
    0.47
    ס
    0.46
     Gideon
    0.44
     habitually
    0.44
     Putra
    0.43
     Prima
    0.43
    тый
    0.43
    Activations Density 0.000%

    No Known Activations