© 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. 176375
    Prev
    Next
    INDEX
    Explanations

    personal information

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

    Okay, then, background, faith

    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
     wollen
    0.50
    まずは
    0.49
    媺
    0.49
    驪
    0.48
    この
    0.48
     migliorare
    0.47
     ಹೆಚ್ಚ
    0.47
    Neces
    0.47
     تربيع
    0.46
     মজুদ
    0.46
    POSITIVE LOGITS
     nowrap
    0.52
     全部
    0.50
    yml
    0.47
     Happened
    0.46
     .$
    0.45
    dc
    0.44
    ial
    0.43
    配置文件
    0.43
     Fragment
    0.42
    atorium
    0.42
    Activations Density 0.000%

    No Known Activations