© 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. 198564
    Prev
    Next
    INDEX
    Explanations

    want to call

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

    reporting and analyzing data

    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
    Not in Any Lists

    No Comments

    Negative Logits
     znajdują
    0.48
     unul
    0.47
     Tensorflow
    0.46
     befind
    0.45
    冯
    0.45
     Satu
    0.45
     Giải
    0.45
     Münster
    0.45
     chá
    0.45
     penyakit
    0.44
    POSITIVE LOGITS
    iros
    0.46
    rex
    0.46
    ਜ
    0.45
     ইয়াহিয়ার
    0.43
    reif
    0.43
    rova
    0.40
    この記事
    0.40
     onDestroy
    0.40
    Splash
    0.39
    roj
    0.39
    Activations Density 0.000%

    No Known Activations