© 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. 103625
    Prev
    Next
    INDEX
    Explanations

    information and new in various languages

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

    ask me, formulas, focus on

    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
     основным
    0.52
    ন
    0.43
    表明
    0.43
     安全
    0.43
    ጸ
    0.43
    实例化
    0.42
     大型
    0.41
     QLabel
    0.40
    6
    0.40
    ependent
    0.40
    POSITIVE LOGITS
     bilgi
    0.50
    wurf
    0.47
     neue
    0.47
     Informationen
    0.47
     الجديد
    0.46
    ത്തു
    0.46
     kung
    0.46
     bunlar
    0.46
    neux
    0.46
     informacije
    0.46
    Activations Density 0.001%

    No Known Activations